© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16995
    Prev
    Next
    INDEX
    Explanations

    proper nouns and terms related to academic institutions and events

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and related activities

    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
    conservancy
    -0.91
    .ãĢį
    -0.84
     reluct
    -0.83
     tremend
    -0.77
    itely
    -0.76
    pill
    -0.74
    taboola
    -0.74
    rising
    -0.73
     answ
    -0.73
    quart
    -0.72
    POSITIVE LOGITS
     Miscellaneous
    1.17
     Various
    1.03
     Others
    0.94
     ----------------------------------------------------------------
    0.94
     The
    0.94
     Other
    0.94
     âĵĺ
    0.91
     Total
    0.91
     Any
    0.91
     Conclusion
    0.91
    Activations Density 0.293%

    No Known Activations