© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    questions related to knowledge and understanding

    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
    476
    +0.03
    0.5%
    762
    +0.03
    0.5%
    396
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.03
    0.03
    60
    +0.03
    0.03
    119
    +0.03
    0.03
    Negative Logits
    phrine
    -0.26
    ãĥĥãĥī
    -0.20
    ahime
    -0.19
    mes
    -0.18
     somewhere
    -0.18
    ENE
    -0.18
     Swordsman
    -0.18
    代
    -0.18
    escription
    -0.17
     Hels
    -0.17
    POSITIVE LOGITS
    Newsletter
    0.20
    VERTISEMENT
    0.19
    agree
    0.18
     respondent
    0.18
     approves
    0.17
    reat
    0.17
    claimer
    0.17
    dep
    0.17
    Roll
    0.17
    trust
    0.17
    Activations Density 0.123%

    No Known Activations