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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33088
    Prev
    Next
    INDEX
    Explanations

    words related to breadth or broadness, such as "broad" or "broadest."

    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
    99
    +0.14
    0.7%
    447
    +0.14
    0.7%
    67
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    743
    +0.14
    0.06
    426
    +0.14
    0.06
    167
    +0.11
    -0.03
    Negative Logits
    LV
    -0.76
     Tycoon
    -0.73
    ICAN
    -0.72
     Keeper
    -0.68
    USD
    -0.65
     Disciple
    -0.65
    CB
    -0.64
    IENCE
    -0.63
    ILLE
    -0.63
     Million
    -0.63
    POSITIVE LOGITS
    sheet
    1.44
    sheets
    1.26
    ening
    1.11
    leaf
    1.08
    sword
    1.03
     spectrum
    0.96
     strokes
    0.95
    ened
    0.93
    side
    0.92
     outlines
    0.84
    Activations Density 7.439%

    No Known Activations