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. 34355
    Prev
    Next
    INDEX
    Explanations

    places or events related to historical conflicts or tragedies

    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
    +0.18
    0.9%
    121
    +0.11
    0.5%
    639
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.18
    0.14
    14
    +0.11
    0.05
    743
    +0.10
    0.05
    Negative Logits
    natureconservancy
    -0.74
    soDeliveryDate
    -0.70
    wcsstore
    -0.68
    UA
    -0.65
    agall
    -0.65
    clus
    -0.64
    aughty
    -0.63
    ÙĴ
    -0.63
    utical
    -0.62
    erd
    -0.62
    POSITIVE LOGITS
     ransom
    0.78
     crem
    0.69
     resurrection
    0.68
    mur
    0.67
     syndrome
    0.66
     Syndrome
    0.64
     coma
    0.64
     coroner
    0.64
     autopsy
    0.63
     martyr
    0.62
    Activations Density 29.031%

    No Known Activations