© 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. 1781
    Prev
    Next
    INDEX
    Explanations

    computer programming terms and functions

    oai_token-act-pair · gpt-3.5-turbo

    references to educational materials or programs

    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
    ilipp
    -0.79
    ueller
    -0.67
     confir
    -0.64
    tsky
    -0.62
    });
    -0.61
     prevailed
    -0.60
     curfew
    -0.60
    ibly
    -0.59
     trou
    -0.58
    azeera
    -0.58
    POSITIVE LOGITS
     Provides
    0.88
     Located
    0.86
     Allows
    0.81
     Another
    0.79
    formerly
    0.78
    Used
    0.78
     Cosponsors
    0.74
     Increases
    0.74
     Uses
    0.74
     Contains
    0.73
    Activations Density 0.251%

    No Known Activations