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. 7-RES-JB
    6. 20491
    Prev
    Next
    INDEX
    Explanations

    names of cyclists and specific race-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cycling events and participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.80
    hattan
    -0.76
     Barron
    -0.75
    ername
    -0.72
    iple
    -0.71
     Onion
    -0.70
    abbage
    -0.69
     Neighbor
    -0.69
    reve
    -0.68
    lishes
    -0.68
    POSITIVE LOGITS
     doping
    1.06
     cycling
    1.05
     Cycling
    0.97
     BMC
    0.91
     tyre
    0.91
     rider
    0.91
     sprint
    0.90
     endurance
    0.88
     racing
    0.82
     cyclist
    0.81
    Activations Density 0.157%

    No Known Activations