© 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. 6463
    Prev
    Next
    INDEX
    Explanations

    actions happening in a sequence with specific individuals involved in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of timing or sequential actions

    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
    arnaev
    -0.80
    anmar
    -0.79
     Historically
    -0.78
    zbollah
    -0.78
     Nation
    -0.70
    agate
    -0.69
    efeated
    -0.68
    ynasty
    -0.66
     Nobel
    -0.64
     Founders
    -0.63
    POSITIVE LOGITS
     exhaustion
    0.82
     exclaim
    0.77
     shouting
    0.76
     laughter
    0.76
     yelling
    0.76
     coughing
    0.73
     rhyth
    0.73
     repet
    0.72
     grabbing
    0.72
     gigg
    0.71
    Activations Density 0.478%

    No Known Activations