© 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. 4127
    Prev
    Next
    INDEX
    Explanations

    keywords related to customization and specialized features or actions within applications or devices

    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
    +0.24
    1.1%
    302
    +0.13
    0.6%
    70
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.24
    0.06
    70
    +0.13
    0.08
    237
    +0.12
    0.05
    Negative Logits
    ï¸
    -0.81
     CrossRef
    -0.76
    Æ
    -0.73
     Kinn
    -0.72
     Lauder
    -0.72
    trump
    -0.72
     Mub
    -0.72
    loo
    -0.72
     Yose
    -0.72
    wick
    -0.72
    POSITIVE LOGITS
    isable
    1.52
    izations
    1.42
    isations
    1.24
    arily
    1.19
    ised
    1.17
    izable
    1.15
    isation
    1.11
    ization
    0.95
     tailored
    0.94
    izing
    0.86
    Activations Density 7.897%

    No Known Activations