© 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 Local
    5. 6-RES_SCL-AJT
    6. 32284
    Prev
    Next
    INDEX
    Explanations

    proper names and places such as "Strathallan" and "Anstruther."

    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
    385
    +0.09
    0.4%
    587
    +0.08
    0.4%
    447
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.09
    0.10
    398
    +0.08
    0.07
    556
    +0.08
    0.07
    Negative Logits
    ufact
    -0.73
    nih
    -0.61
     sugg
    -0.60
     admission
    -0.59
     Admission
    -0.58
     adrenaline
    -0.58
    ITNESS
    -0.56
    ittance
    -0.55
    yright
    -0.55
     WATCH
    -0.54
    POSITIVE LOGITS
    upon
    0.71
    utsche
    0.68
     confines
    0.68
    ioxide
    0.63
    ngth
    0.62
    ivari
    0.61
    ordes
    0.60
    bourg
    0.60
     ISI
    0.60
    iers
    0.59
    Activations Density 12.018%

    No Known Activations