© 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. 6907
    Prev
    Next
    INDEX
    Explanations

    [A]rticles discussing various matters or topics

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that introduce additional context or commentary

    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
    catentry
    -0.85
    scribe
    -0.72
    hash
    -0.68
    irie
    -0.67
    chio
    -0.64
    ioxide
    -0.63
    iple
    -0.62
    hene
    -0.62
    ussie
    -0.61
    thora
    -0.61
    POSITIVE LOGITS
     namely
    1.48
     albeit
    1.11
     wherein
    1.00
     though
    0.94
     according
    0.93
     whereby
    0.92
     however
    0.90
     claiming
    0.90
     culminating
    0.90
     although
    0.88
    Activations Density 0.375%

    No Known Activations