© 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
    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. 12826
    Prev
    Next
    INDEX
    Explanations

    references to various historical events and figures

    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
    +0.30
    1.2%
    191
    +0.15
    0.6%
    721
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.30
    0.12
    123
    +0.15
    0.11
    220
    +0.13
    0.10
    Negative Logits
    Ô
    -0.78
    shape
    -0.71
    Desktop
    -0.70
    pron
    -0.69
    SHARE
    -0.69
    ãĤµ
    -0.68
    ndra
    -0.68
    uay
    -0.67
    prototype
    -0.67
    edom
    -0.66
    POSITIVE LOGITS
     âĨij
    1.17
     ff
    1.13
     seq
    0.96
    0002
    0.95
     quoting
    0.91
    .;
    0.88
     footnote
    0.86
     Ibid
    0.86
    69
    0.85
    349
    0.85
    Activations Density 10.074%

    No Known Activations