© 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. 45872
    Prev
    Next
    INDEX
    Explanations

    information related to software configuration settings

    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
    +0.20
    0.8%
    145
    +0.12
    0.5%
    222
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.23
    640
    +0.12
    0.20
    362
    +0.12
    0.10
    Negative Logits
    ewitness
    -0.88
    ulty
    -0.87
    iculty
    -0.82
    adeon
    -0.81
    igslist
    -0.79
    emouth
    -0.77
    isance
    -0.76
    ocobo
    -0.75
    psey
    -0.72
    ophe
    -0.72
    POSITIVE LOGITS
     undefined
    1.00
     null
    0.98
     {"
    0.97
     None
    0.97
     {}
    0.95
     nil
    0.92
     False
    0.91
     false
    0.89
     NULL
    0.88
     none
    0.86
    Activations Density 7.336%

    No Known Activations