© 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. 39894
    Prev
    Next
    INDEX
    Explanations

    phrases related to recent events and observations

    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%
    244
    +0.11
    0.5%
    610
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.24
    0.16
    370
    +0.11
    0.07
    393
    +0.10
    0.32
    Negative Logits
    amba
    -0.73
     beforehand
    -0.66
     Originally
    -0.64
     Patel
    -0.61
     otherwise
    -0.60
    quet
    -0.59
     portfolios
    -0.58
    una
    -0.58
     anecdote
    -0.58
    odor
    -0.58
    POSITIVE LOGITS
    EEK
    0.80
    Ô
    0.77
     finally
    0.76
    LEASE
    0.75
    WIND
    0.72
    FIN
    0.70
    YA
    0.68
    ANCE
    0.67
     FIN
    0.66
     unravel
    0.65
    Activations Density 18.638%

    No Known Activations