© 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. 10-RES-JB
    11. 9918
    Prev
    Next
    INDEX
    Explanations

    names of politicians and mentions of political actions or positions

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britann
    -0.76
     LTD
    -0.76
     Yugoslav
    -0.73
     civilisation
    -0.69
     Siberian
    -0.69
     Kinnikuman
    -0.68
     Tycoon
    -0.68
    DragonMagazine
    -0.66
    properties
    -0.66
     Miracle
    -0.66
    POSITIVE LOGITS
    ospons
    1.48
    osponsors
    1.41
     filib
    1.36
     chairs
    1.18
     voted
    1.16
     Subcommittee
    1.15
     caucus
    1.10
     subcommittee
    1.09
     Caucus
    1.09
     caucuses
    1.09
    Activations Density 0.320%

    No Known Activations