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. 13301
    Prev
    Next
    INDEX
    Explanations

    scientific and astronomical terms and concepts

    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
    +0.12
    0.6%
    326
    +0.10
    0.6%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.18
    326
    +0.10
    0.18
    271
    +0.10
    0.04
    Negative Logits
    plings
    -0.64
    isode
    -0.63
    incerity
    -0.61
    ividual
    -0.61
    Interstitial
    -0.61
    inki
    -0.58
    idation
    -0.58
    lain
    -0.57
    xit
    -0.56
    igan
    -0.56
    POSITIVE LOGITS
     astronomers
    0.99
     astronomer
    0.89
    omical
    0.88
     telescope
    0.85
     astroph
    0.85
     Telescope
    0.83
     telescopes
    0.82
     Astron
    0.78
    omy
    0.75
     Observatory
    0.74
    Activations Density 6.446%

    No Known Activations