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

    Neuronpedia

    APICircuit 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. 13316
    Prev
    Next
    INDEX
    Explanations

    mentions or references to someone's death

    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%
    468
    +0.12
    0.5%
    210
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.32
    618
    +0.12
    0.17
    6
    +0.12
    0.17
    Negative Logits
    GY
    -0.77
    rouse
    -0.76
    umar
    -0.76
    MAT
    -0.72
    alos
    -0.71
    Pros
    -0.71
    ãĥ¢
    -0.71
    å§«
    -0.70
    asers
    -0.68
    uu
    -0.68
    POSITIVE LOGITS
     tragically
    1.06
     psychiat
    0.88
     intest
    0.85
     retire
    0.84
     Surv
    0.84
     prematurely
    0.83
    uary
    0.81
     retiring
    0.80
     aged
    0.78
     mysteriously
    0.78
    Activations Density 13.260%

    No Known Activations