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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9689
    Prev
    Next
    INDEX
    Explanations

    references to being on the sidelines or sidelines themselves

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sideline" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eric
    -0.64
    gran
    -0.64
    eros
    -0.63
    ettel
    -0.63
    Operation
    -0.63
    Progress
    -0.62
    GB
    -0.61
    Lear
    -0.61
    Hen
    -0.60
    York
    -0.60
    POSITIVE LOGITS
     sidelines
    1.34
     sideline
    0.87
    MpServer
    0.86
    swer
    0.83
    side
    0.81
    ilage
    0.76
    pole
    0.73
    bilt
    0.72
    ngth
    0.70
    staff
    0.69
    Activations Density 0.003%

    No Known Activations