Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45186
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically referring to various locations and people

    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
    +0.16
    0.8%
    187
    +0.14
    0.7%
    195
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.20
    314
    +0.14
    -0.04
    6
    +0.13
    0.13
    Negative Logits
    sburgh
    -0.89
    ettings
    -0.81
    vironment
    -0.78
    ysis
    -0.70
    uality
    -0.68
    ichick
    -0.65
    ually
    -0.65
     Kinn
    -0.63
    essee
    -0.63
    isance
    -0.61
    POSITIVE LOGITS
    rier
    1.00
    riers
    0.97
    aday
    0.92
    thing
    0.92
    ouk
    0.87
    rer
    0.86
    rak
    0.86
    ghan
    0.84
    rug
    0.82
    az
    0.81
    Activations Density 7.680%

    No Known Activations