© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events happening next

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "But then" to indicate a shift or contrast in the narrative

    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
    toe
    -0.73
    ties
    -0.68
    Latin
    -0.67
    ours
    -0.65
    leading
    -0.64
    tein
    -0.64
    orde
    -0.64
    TE
    -0.64
    ãĥĸ
    -0.62
    SUP
    -0.62
    POSITIVE LOGITS
     again
    0.91
     suddenly
    0.89
     abruptly
    0.85
     proceeded
    0.83
     comes
    0.78
     mysteriously
    0.76
     secondly
    0.74
     disappears
    0.72
     forgot
    0.71
     remembered
    0.70
    Activations Density 0.053%

    No Known Activations