© 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 Local
    9. 6-RES_SCL-AJT
    11. 4669
    Prev
    Next
    INDEX
    Explanations

    baking instructions and ingredients for a recipe

    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
    274
    +0.11
    0.6%
    455
    +0.10
    0.6%
    540
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.11
    0.19
    23
    +0.10
    0.12
    129
    +0.10
    0.09
    Negative Logits
    actionDate
    -0.82
    EStream
    -0.66
    NetMessage
    -0.60
    hammad
    -0.60
    REDACTED
    -0.58
    cffff
    -0.57
    nesota
    -0.57
    oleon
    -0.57
    EStreamFrame
    -0.57
    ertodd
    -0.56
    POSITIVE LOGITS
    still
    1.00
    bys
    0.85
    ings
    0.83
    pipe
    0.76
    outs
    0.73
    ances
    0.70
    ingly
    0.69
    ards
    0.68
    ivities
    0.67
    mount
    0.66
    Activations Density 9.688%

    No Known Activations