© 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. 34747
    Prev
    Next
    INDEX
    Explanations

    references to power struggles and conflicts, particularly in a medieval or fantasy setting

    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
    288
    +0.15
    0.7%
    311
    +0.14
    0.7%
    284
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.15
    0.04
    456
    +0.14
    0.06
    403
    +0.13
    0.04
    Negative Logits
    STON
    -0.67
    士
    -0.64
    manship
    -0.62
    BY
    -0.61
    hold
    -0.61
    creen
    -0.61
    ETS
    -0.61
    女
    -0.61
     Blaz
    -0.59
    LOC
    -0.59
    POSITIVE LOGITS
    imately
    1.23
    iple
    1.13
    raviolet
    1.09
    urally
    1.02
    imates
    1.00
    icultural
    0.92
    ieth
    0.91
    ures
    0.90
    ipl
    0.89
    iful
    0.88
    Activations Density 7.300%

    No Known Activations