© 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. 6714
    Prev
    Next
    INDEX
    Explanations

    legal or official terms, such as statutes, regulations, and official procedures

    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
    196
    +0.03
    0.6%
    239
    +0.03
    0.5%
    49
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.02
    373
    +0.03
    -0.01
    255
    +0.03
    0.01
    Negative Logits
     Nare
    -0.20
    rade
    -0.20
    ée
    -0.19
     Lowell
    -0.19
     Mehran
    -0.18
    ]]
    -0.18
    ovie
    -0.18
     Anthem
    -0.18
    >:
    -0.17
     proposes
    -0.17
    POSITIVE LOGITS
    mc
    0.16
    Clark
    0.16
    assets
    0.16
    çĭ
    0.16
    gm
    0.16
    TE
    0.16
    GMT
    0.16
    anos
    0.15
    Test
    0.15
    IU
    0.15
    Activations Density 0.037%

    No Known Activations