© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32134
    Prev
    Next
    INDEX
    Explanations

    words related to historical events and slavery

    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
    216
    +0.08
    0.5%
    376
    +0.08
    0.5%
    484
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.08
    0.28
    393
    +0.08
    0.29
    33
    +0.07
    0.09
    Negative Logits
    é¾įå¥ij士
    -0.57
    sembly
    -0.55
    naires
    -0.53
    ymes
    -0.51
    ĨĴ
    -0.51
    ãĥĥãĥĪ
    -0.50
     CLSID
    -0.48
    andestine
    -0.48
     MSM
    -0.47
    pport
    -0.47
    POSITIVE LOGITS
    olina
    1.01
    negie
    0.92
    ousel
    0.91
    rier
    0.84
    oline
    0.83
    olyn
    0.83
    riage
    0.79
    riers
    0.76
    bon
    0.74
    riages
    0.74
    Activations Density 14.052%

    No Known Activations