© 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. 31337
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical arguments and beliefs

    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
    248
    +0.15
    0.7%
    481
    +0.13
    0.6%
    458
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.18
    526
    +0.13
    -0.03
    608
    +0.12
    0.22
    Negative Logits
    ascript
    -0.96
    nom
    -0.78
    ufficient
    -0.78
    amiya
    -0.77
    catentry
    -0.77
     sidx
    -0.76
    ptives
    -0.75
    agascar
    -0.74
    âĸij
    -0.73
    inventoryQuantity
    -0.73
    POSITIVE LOGITS
     him
    1.07
     unsuspecting
    1.03
     yourself
    0.98
    erous
    0.98
     oneself
    0.95
     yourselves
    0.94
     us
    0.93
     HIM
    0.92
     me
    0.90
     himself
    0.89
    Activations Density 10.859%

    No Known Activations