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. 40288
    Prev
    Next
    INDEX
    Explanations

    mentions of Sarah Palin and related topics such as interviews, news conferences, investigations, and public safety commissioners

    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
    +0.15
    0.6%
    57
    +0.13
    0.5%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.12
    659
    +0.13
    0.10
    346
    +0.11
    0.09
    Negative Logits
    ivity
    -0.77
     Aether
    -0.77
    onet
    -0.74
     Rao
    -0.72
     Indo
    -0.70
    ±
    -0.68
     antioxid
    -0.67
     Agric
    -0.67
     Orion
    -0.67
    OX
    -0.66
    POSITIVE LOGITS
     aides
    0.92
     Huckabee
    0.89
    etz
    0.82
    cci
    0.79
     aide
    0.77
     disav
    0.75
    lication
    0.75
    addafi
    0.72
     Palin
    0.72
    nr
    0.71
    Activations Density 5.208%

    No Known Activations