© 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
    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. 39483
    Prev
    Next
    INDEX
    Explanations

    physical actions or medical terms related to wounds, injuries, or violence

    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
    99
    +0.10
    0.6%
    288
    +0.09
    0.5%
    45
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    -0.03
    640
    +0.09
    0.23
    143
    +0.09
    0.07
    Negative Logits
    utical
    -0.65
    llah
    -0.64
    ptive
    -0.60
    çĦ
    -0.58
    ptives
    -0.55
    andro
    -0.52
    ãģ®éŃĶ
    -0.50
    Bi
    -0.50
     Bei
    -0.49
    cale
    -0.49
    POSITIVE LOGITS
    ibility
    0.83
    verted
    0.75
    version
    0.73
    icals
    0.70
    ible
    0.67
    ophobia
    0.66
    igo
    0.66
    verts
    0.65
    verting
    0.63
    ibly
    0.59
    Activations Density 11.495%

    No Known Activations