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. 2-RES-JB
    6. 10731
    Prev
    Next
    INDEX
    Explanations

    references to actions or objects related to physically raising a fist

    oai_token-act-pair · gpt-3.5-turbo

    references to "fist" or "fists"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Marginal
    -0.85
    Trend
    -0.81
    acent
    -0.75
    Sleep
    -0.74
     Agency
    -0.73
    Smart
    -0.71
    DIT
    -0.70
    Demand
    -0.68
     Living
    -0.68
     Comfort
    -0.67
    POSITIVE LOGITS
     fist
    1.09
     clen
    0.97
     fists
    0.89
     clenched
    0.89
     salute
    0.88
    fights
    0.86
    uffs
    0.81
    rican
    0.80
    rag
    0.80
     smack
    0.77
    Activations Density 0.006%

    No Known Activations