© 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. 4019
    Prev
    Next
    INDEX
    Explanations

    names of individuals in a news story

    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
    +0.44
    2.1%
    481
    +0.18
    0.9%
    171
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.44
    0.25
    420
    +0.18
    0.14
    563
    +0.11
    0.15
    Negative Logits
    wcs
    -0.73
    incarn
    -0.66
     Werewolf
    -0.61
     Klux
    -0.61
     Birthday
    -0.61
    Origin
    -0.60
    population
    -0.60
     Bigfoot
    -0.59
     Triple
    -0.59
    itary
    -0.58
    POSITIVE LOGITS
     concludes
    0.88
     concede
    0.85
     emphasized
    0.84
     explained
    0.84
     laughed
    0.84
     conceded
    0.83
     laughs
    0.83
     emphasizes
    0.82
     elaborated
    0.82
     concedes
    0.79
    Activations Density 20.030%

    No Known Activations