© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1984
    Prev
    Next
    INDEX
    Explanations

    references to textbooks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.18
    0.9%
    437
    +0.11
    0.5%
    365
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.07
    575
    +0.11
    0.06
    614
    +0.11
    0.03
    Negative Logits
    ths
    -0.71
    oresc
    -0.66
    ods
    -0.64
    iva
    -0.62
    inion
    -0.62
    thy
    -0.61
    phant
    -0.60
     territ
    -0.60
    hart
    -0.59
     brighter
    -0.59
    POSITIVE LOGITS
    ãĤ¢ãĥ«
    0.79
     textbook
    0.77
     vit
    0.73
    ÄŁ
    0.71
    urally
    0.69
    eteria
    0.67
    oons
    0.66
    TeX
    0.66
    esome
    0.66
    cases
    0.64
    Activations Density 0.505%

    No Known Activations