Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 33245
    Prev
    Next
    INDEX
    Explanations

    code-related terms and programming instructions

    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
    +0.23
    0.9%
    393
    +0.18
    0.7%
    640
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.23
    0.34
    447
    +0.18
    0.36
    64
    +0.16
    -0.24
    Negative Logits
     Lowry
    -0.85
     Norris
    -0.80
     Cassidy
    -0.75
     Gilmore
    -0.74
     Gallup
    -0.73
     Dys
    -0.73
    ierrez
    -0.72
     Cotton
    -0.72
     Gunn
    -0.72
    esson
    -0.71
    POSITIVE LOGITS
    generic
    1.23
    mode
    1.22
    level
    1.20
    based
    1.17
    utils
    1.14
    input
    1.13
    cache
    1.13
    value
    1.12
    setup
    1.12
    spec
    1.10
    Activations Density 15.087%

    No Known Activations