© 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. 9-RES-JB
    11. 5216
    Prev
    Next
    INDEX
    Explanations

    objects or items that are wrapped or draped in a specific way

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reward
    -0.77
    ancies
    -0.73
    iances
    -0.67
    conom
    -0.67
    ancy
    -0.65
    alty
    -0.63
     Explorer
    -0.63
    ahime
    -0.63
    Export
    -0.62
    Britain
    -0.62
    POSITIVE LOGITS
     neatly
    1.07
     atop
    1.05
     onto
    0.97
     upside
    0.95
     tightly
    0.92
     firmly
    0.91
     horizontally
    0.91
     aback
    0.91
     beneath
    0.90
     snug
    0.89
    Activations Density 0.182%

    No Known Activations