© 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. 6936
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms, particularly those associated with legislative contexts

    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
     timet
    -0.81
     uncontroll
    -0.74
     maturity
    -0.71
     intrinsic
    -0.71
     tolerance
    -0.71
     ceilings
    -0.69
     blame
    -0.68
     margins
    -0.68
     rhy
    -0.68
     prejudice
    -0.67
    POSITIVE LOGITS
    Washington
    1.06
    Portland
    1.02
    Seattle
    1.00
    Calif
    0.99
    Florida
    0.98
    California
    0.97
    Chicago
    0.96
    achusetts
    0.96
    Philadelphia
    0.94
    rament
    0.92
    Activations Density 0.018%

    No Known Activations