© 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. 9-RES-JB
    11. 2456
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for specific actions from individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.99
    ãĤ§
    -0.74
    ixture
    -0.72
    tics
    -0.71
    ella
    -0.71
    ãĤ¤ãĥĪ
    -0.70
    ãĤ¡
    -0.70
     thrill
    -0.69
     sidx
    -0.69
    ãĥĥãĥī
    -0.69
    POSITIVE LOGITS
     policymakers
    1.41
     Governments
    1.36
     governments
    1.33
     Congress
    1.31
     legislators
    1.30
     Governor
    1.26
     lawmakers
    1.22
    Govern
    1.20
     Gov
    1.20
     Government
    1.19
    Activations Density 0.816%

    No Known Activations