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. 45405
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles or positions related to leadership roles, such as president, CEO, chief executive, etc

    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
    +0.34
    1.6%
    393
    +0.20
    0.9%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.34
    0.27
    669
    +0.20
    0.12
    393
    +0.10
    0.25
    Negative Logits
     stub
    -0.82
    dayName
    -0.65
     relate
    -0.64
     complicate
    -0.61
     degrade
    -0.61
     humili
    -0.60
     overwrite
    -0.60
     pretext
    -0.59
     haircut
    -0.58
     worsen
    -0.58
    POSITIVE LOGITS
     Liberty
    0.75
     Towns
    0.74
     Gale
    0.68
     Photography
    0.67
     Sierra
    0.67
     Maple
    0.66
     Montreal
    0.66
     Aires
    0.66
     Clubs
    0.65
    icial
    0.65
    Activations Density 11.096%

    No Known Activations