© 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. 13767
    Prev
    Next
    INDEX
    Explanations

    technical information related to research methods and experiments

    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
    447
    +0.28
    1.3%
    356
    +0.12
    0.6%
    58
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.28
    0.14
    326
    +0.12
    0.20
    201
    +0.10
    0.09
    Negative Logits
    ierrez
    -0.73
    agine
    -0.72
    ogene
    -0.71
    iliated
    -0.68
     plateau
    -0.66
    querque
    -0.65
    isode
    -0.64
    inations
    -0.64
     snowball
    -0.62
    chio
    -0.62
    POSITIVE LOGITS
    00
    1.15
    50
    1.14
    70
    1.08
    60
    1.07
    80
    1.05
    40
    1.04
    30
    1.03
    01
    1.03
    20
    0.98
    75
    0.98
    Activations Density 8.477%

    No Known Activations