© 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. 2493
    Prev
    Next
    INDEX
    Explanations

    action-related words such as sending, moving, or doing

    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
     Seym
    -0.70
    licted
    -0.69
    attering
    -0.58
    esides
    -0.56
    livious
    -0.55
    riks
    -0.54
     Vaugh
    -0.53
    arthed
    -0.52
    iuses
    -0.51
     anecd
    -0.51
    POSITIVE LOGITS
     RELEASE
    0.95
     ASAP
    0.79
     Continued
    0.61
     someday
    0.60
    .--
    0.58
     Reply
    0.58
    "?
    0.57
    %:
    0.57
    morrow
    0.56
     Ratio
    0.55
    Activations Density 0.380%

    No Known Activations