© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6610
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for intervention in various situations

    oai_token-act-pair · gpt-3.5-turbo

    statements about calls to action or requests for intervention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.84
    ãĤ¡
    -0.79
    igmatic
    -0.73
    ãĤ©
    -0.72
    Untitled
    -0.72
    apes
    -0.70
    erenn
    -0.70
    amac
    -0.69
    ateral
    -0.69
    vable
    -0.69
    POSITIVE LOGITS
     policymakers
    1.24
     lawmakers
    1.19
     legislators
    1.14
     Congress
    1.06
     governments
    1.06
     politicians
    1.01
     voters
    0.99
     colleagues
    0.99
     ministers
    0.99
     senators
    0.98
    Activations Density 0.088%

    No Known Activations