© 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 EvalsExportsAPI 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. 291
    Prev
    Next
    INDEX
    Explanations

    items or substances that are preferred or favored for specific purposes

    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
    190
    +0.02
    0.4%
    485
    +0.02
    0.4%
    664
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.02
    0.03
    512
    +0.02
    0.02
    765
    +0.02
    0.02
    Negative Logits
    adan
    -0.18
    emen
    -0.16
    aman
    -0.16
    odore
    -0.15
    amon
    -0.15
    ivan
    -0.15
    erva
    -0.15
    ements
    -0.15
    raph
    -0.15
    addin
    -0.15
    POSITIVE LOGITS
     forks
    0.16
     suspects
    0.14
     sticks
    0.14
     killers
    0.13
     Weber
    0.13
     trophies
    0.13
     deploy
    0.13
     bleeding
    0.13
     implements
    0.13
    ãĥ³ãĤ¸
    0.13
    Activations Density 0.159%

    No Known Activations