© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 11302
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms related to different topics

    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
    569
    +0.21
    0.8%
    549
    +0.16
    0.6%
    701
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.09
    701
    +0.16
    0.05
    326
    +0.14
    0.07
    Negative Logits
    andowski
    -0.94
    yers
    -0.92
    orters
    -0.89
    yang
    -0.89
    ez
    -0.85
    lain
    -0.85
    ing
    -0.83
    eva
    -0.82
    erto
    -0.82
    BOOK
    -0.81
    POSITIVE LOGITS
    odon
    1.10
    actic
    0.97
    raft
    0.93
    ãĥ¥
    0.92
    axy
    0.90
     Cyn
    0.84
     parasite
    0.83
     mammal
    0.80
    plane
    0.79
    etheless
    0.79
    Activations Density 0.780%

    No Known Activations