© 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. 10-RES-JB
    11. 17388
    Prev
    Next
    INDEX
    Explanations

    adjectives describing things that are noteworthy or outstanding

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and present participles that describe unusual or striking situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obook
    -0.68
    ailable
    -0.67
    athan
    -0.66
    ______
    -0.66
    umbn
    -0.63
    /
    -0.61
    Ïī
    -0.61
    essage
    -0.61
    anni
    -0.61
    authorized
    -0.60
    POSITIVE LOGITS
    ly
    0.99
     enough
    0.89
     observers
    0.87
    nesses
    0.87
     caveats
    0.85
     irony
    0.85
     glances
    0.84
    LY
    0.83
     examples
    0.82
     gestures
    0.81
    Activations Density 0.323%

    No Known Activations