© 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. 6206
    Prev
    Next
    INDEX
    Explanations

    texts discussing lists of items or topics

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to financial evaluations or assessments

    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
    iage
    -0.74
    mage
    -0.72
    pent
    -0.72
    UME
    -0.67
    akery
    -0.67
    tm
    -0.66
    tree
    -0.66
    uca
    -0.65
    ae
    -0.65
    estate
    -0.65
    POSITIVE LOGITS
     acron
    1.03
     noteworthy
    1.00
     highlights
    0.99
     names
    0.95
     notable
    0.95
     accomplishments
    0.94
     quotes
    0.91
     milestones
    0.88
     reactions
    0.88
     examples
    0.87
    Activations Density 0.194%

    No Known Activations