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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11-RES-JB
    6. 3199
    Prev
    Next
    INDEX
    Explanations

    strong actions or reactions, like fighting, working, campaigning, or reacting

    oai_token-act-pair · gpt-3.5-turbo

    actions related to conflict, effort, and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.82
    Companies
    -0.65
     };
    -0.63
     Nutrition
    -0.63
     Potential
    -0.62
     Funding
    -0.61
     Purch
    -0.61
    arent
    -0.61
     IF
    -0.60
    ./
    -0.60
    POSITIVE LOGITS
     brilliantly
    1.54
     wonderfully
    1.36
     remarkably
    1.36
     beautifully
    1.35
     furiously
    1.35
     relentlessly
    1.33
     powerfully
    1.33
     tirelessly
    1.28
     deft
    1.26
     vividly
    1.26
    Activations Density 0.391%

    No Known Activations