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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13172
    Prev
    Next
    INDEX
    Explanations

    phrases related to intelligence and design

    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
    679
    +0.16
    0.8%
    447
    +0.14
    0.7%
    356
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.20
    356
    +0.14
    0.02
    613
    +0.13
    0.08
    Negative Logits
    soDeliveryDate
    -0.70
    laus
    -0.67
     Bundy
    -0.67
    MY
    -0.67
     Soda
    -0.65
    rine
    -0.64
    raine
    -0.64
    ield
    -0.63
    jer
    -0.63
     Gazette
    -0.62
    POSITIVE LOGITS
     quot
    0.95
    elligent
    0.90
     intellig
    0.74
    ively
    0.73
    elligence
    0.71
    Reviewer
    0.68
     intelligent
    0.68
     beings
    0.65
    heid
    0.62
    mble
    0.62
    Activations Density 6.998%

    No Known Activations