© 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. 24019
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or events involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    key entities and actions related to events, particularly those involving legal or political contexts

    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
    depending
    -0.59
     lately
    -0.55
    nesday
    -0.51
     nowadays
    -0.51
     endeavour
    -0.50
     recent
    -0.49
    ichever
    -0.48
     depends
    -0.48
    anie
    -0.48
     varies
    -0.47
    POSITIVE LOGITS
    .[
    0.84
     again
    0.70
    ."[
    0.69
    .]
    0.69
    and
    0.69
    .
    0.68
     and
    0.68
     anew
    0.67
     AND
    0.66
    again
    0.65
    Activations Density 1.067%

    No Known Activations