© 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. 7559
    Prev
    Next
    INDEX
    Explanations

    technical details related to computer hardware and technology

    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
    580
    +0.13
    0.5%
    339
    +0.11
    0.4%
    501
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.34
    575
    +0.11
    0.20
    247
    +0.11
    0.10
    Negative Logits
    ttes
    -0.83
    aminer
    -0.81
    utenberg
    -0.79
    choes
    -0.76
    changes
    -0.76
    Adds
    -0.74
    ãĥĺãĥ©
    -0.73
     Seym
    -0.73
     Ake
    -0.72
    oute
    -0.72
    POSITIVE LOGITS
     astronauts
    0.82
     astronaut
    0.78
    \'
    0.77
    iversary
    0.73
     homebrew
    0.73
     lab
    0.72
    gren
    0.72
     outlaw
    0.71
    ui
    0.71
    hiro
    0.70
    Activations Density 8.407%

    No Known Activations