© 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. 45919
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists or groupings of items

    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
    129
    +0.10
    0.5%
    288
    +0.09
    0.5%
    513
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.19
    513
    +0.09
    0.11
    129
    +0.09
    0.08
    Negative Logits
    prints
    -0.65
    abad
    -0.61
    ities
    -0.59
     Gutenberg
    -0.56
    agate
    -0.55
     ABE
    -0.55
    istan
    -0.54
    ippi
    -0.53
    mobi
    -0.52
     nearest
    -0.51
    POSITIVE LOGITS
     of
    0.65
    dozen
    0.64
    ingly
    0.62
     consisting
    0.60
    ographically
    0.60
    mount
    0.59
    ozy
    0.59
    efully
    0.58
    allion
    0.56
    bang
    0.55
    Activations Density 4.702%

    No Known Activations