© 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. 6-RES-JB
    11. 14413
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to famous quotes or statements

    oai_token-act-pair · gpt-3.5-turbo

    textual references, particularly quotes or excerpts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspiration
    -0.69
     amnesty
    -0.67
     Kinder
    -0.66
     visa
    -0.64
     administrator
    -0.64
     Ard
    -0.63
     herself
    -0.63
     unle
    -0.63
     permit
    -0.62
     quota
    -0.61
    POSITIVE LOGITS
    Anyway
    1.21
    ³³³³
    0.97
     Anyway
    0.95
    ³³³³³³³³
    0.93
    ================================================================
    0.90
    Reason
    0.90
    posted
    0.85
    Sharp
    0.84
    ³³³³³³³³³³³³³³³³
    0.83
    References
    0.83
    Activations Density 0.167%

    No Known Activations