© 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. 31277
    Prev
    Next
    INDEX
    Explanations

    phrases related to interviews or news coverage

    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
    71
    +0.13
    0.7%
    393
    +0.12
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.13
    0.05
    393
    +0.12
    0.22
    230
    +0.12
    0.09
    Negative Logits
    chie
    -0.69
    iatus
    -0.61
    resy
    -0.60
    gap
    -0.57
     Cannot
    -0.56
    awaru
    -0.55
     horizon
    -0.55
    chieve
    -0.54
    hill
    -0.54
    gae
    -0.53
    POSITIVE LOGITS
     kinds
    0.92
     sorts
    0.87
    usions
    0.87
    igators
    0.83
    igator
    0.78
    ocating
    0.74
     requisite
    0.69
    usion
    0.69
     necessary
    0.67
    udes
    0.67
    Activations Density 7.872%

    No Known Activations