© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 45828
    Prev
    Next
    INDEX
    Explanations

    specific phrases or patterns related to written text and communication, specifically highlighting mentions of correspondence, publication, and text analysis

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.23
    1.0%
    481
    +0.19
    0.8%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.23
    0.17
    55
    +0.19
    0.16
    184
    +0.11
    0.06
    Negative Logits
    issance
    -0.74
    ndum
    -0.68
    hood
    -0.64
    most
    -0.64
     spokeswoman
    -0.62
    christ
    -0.61
     Counsel
    -0.61
    bart
    -0.60
    onsense
    -0.60
     Advertisement
    -0.60
    POSITIVE LOGITS
     concentrated
    0.84
     clustered
    0.70
     identical
    0.68
     crammed
    0.68
     equally
    0.66
     interchangeable
    0.66
     individually
    0.66
    orted
    0.65
     redundant
    0.65
    ECD
    0.64
    Activations Density 13.522%

    No Known Activations