© 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. 40014
    Prev
    Next
    INDEX
    Explanations

    phrases related to accompanying someone or something

    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
    +0.18
    1.1%
    679
    +0.13
    0.8%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.30
    362
    +0.13
    0.16
    644
    +0.11
    0.13
    Negative Logits
    tery
    -0.59
    theless
    -0.57
    ciples
    -0.56
    holm
    -0.54
    untled
    -0.54
    dam
    -0.52
    etheus
    -0.52
    awar
    -0.52
    roots
    -0.51
     mosque
    -0.51
    POSITIVE LOGITS
    ments
    0.66
    ĸļ
    0.62
    enance
    0.59
     accompanying
    0.56
     Gadget
    0.56
    ocument
    0.56
    iously
    0.53
    Thumbnail
    0.51
    mented
    0.51
    urous
    0.50
    Activations Density 12.484%

    No Known Activations