© 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 Local
    9. 6-RES_SCL-AJT
    11. 34900
    Prev
    Next
    INDEX
    Explanations

    answers to questions or statements that require explanations or reasoning

    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
    447
    +0.22
    1.0%
    195
    +0.12
    0.5%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.22
    0.05
    542
    +0.12
    0.06
    131
    +0.10
    0.05
    Negative Logits
    wana
    -0.89
    ufact
    -0.75
    akin
    -0.72
    awar
    -0.71
    arnaev
    -0.70
    ammy
    -0.70
    erker
    -0.69
    ::::::::
    -0.69
    ombat
    -0.68
     concess
    -0.67
    POSITIVE LOGITS
     answer
    0.95
    answer
    0.93
    ysis
    0.88
     thereto
    0.87
     answ
    0.82
     answered
    0.76
    quickShipAvailable
    0.74
     Answer
    0.74
    Answer
    0.73
     answers
    0.72
    Activations Density 6.707%

    No Known Activations