© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    mentions of political entities, events, and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to political events, institutions, and systems

    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
    ensual
    -0.69
     seams
    -0.66
    pload
    -0.66
    sea
    -0.63
     Biol
    -0.63
    Field
    -0.63
    azy
    -0.62
    ãĤ®
    -0.62
    aylor
    -0.61
     Harbor
    -0.61
    POSITIVE LOGITS
     pund
    0.93
    isans
    0.84
     pundits
    0.83
     appoint
    0.80
     PACs
    0.78
    bent
    0.75
     rhetoric
    0.75
    clinton
    0.75
     populism
    0.74
    âĢİ
    0.73
    Activations Density 0.439%

    No Known Activations