© 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. 36927
    Prev
    Next
    INDEX
    Explanations

    website content-specific information, likely related to news articles

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    388
    +0.03
    0.5%
    1
    +0.03
    0.4%
    157
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.03
    0.08
    126
    +0.03
    0.07
    373
    +0.03
    -0.09
    Negative Logits
     downgrade
    -0.23
    isoft
    -0.22
    lished
    -0.22
     buggy
    -0.20
    issance
    -0.19
    erate
    -0.19
    ufact
    -0.18
    leneck
    -0.18
    hift
    -0.18
     FG
    -0.17
    POSITIVE LOGITS
    onge
    0.25
    usions
    0.23
    important
    0.22
    igator
    0.21
    ure
    0.21
    ocations
    0.21
    uring
    0.21
    udes
    0.20
    ADA
    0.20
    ACC
    0.20
    Activations Density 3.067%

    No Known Activations