© 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. 8-RES-JB
    11. 7605
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events happening at a specific time or location

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating specific moments in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Grade
    -0.63
    ãĥ¡
    -0.63
    hack
    -0.63
    favorite
    -0.61
    equal
    -0.61
    Fine
    -0.61
    95
    -0.59
    Justice
    -0.59
    87
    -0.58
     trimmed
    -0.58
    POSITIVE LOGITS
    soever
    0.94
     suddenly
    0.84
    opus
    0.83
    */(
    0.82
     they
    0.81
     confronted
    0.80
    abouts
    0.78
     she
    0.77
     he
    0.73
     tragedy
    0.72
    Activations Density 0.071%

    No Known Activations