© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3540
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of wood, particularly "Wooden."

    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
    365
    +0.18
    0.6%
    167
    +0.18
    0.6%
    99
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.18
    0.07
    326
    +0.18
    0.07
    365
    +0.18
    0.04
    Negative Logits
    ional
    -1.12
    oresc
    -1.02
    uberty
    -1.01
    OPLE
    -0.93
    orsche
    -0.93
     aver
    -0.93
    egal
    -0.89
    ulsion
    -0.88
    olid
    -0.87
    utations
    -0.87
    POSITIVE LOGITS
    ruff
    1.54
    working
    1.44
    stock
    1.39
    \\\\\\\\
    1.38
    stocks
    1.32
    bridge
    1.30
    leigh
    1.28
    lands
    1.26
    worker
    1.24
    riter
    1.21
    Activations Density 1.350%

    No Known Activations