© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    words related to political events and organizations, specifically referring to events such as conventions and committees within a political party

    oai_token-act-pair · gpt-3.5-turbo

    references to political conventions and committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥ
    -0.76
    Rocket
    -0.74
    etheless
    -0.70
     warr
    -0.70
    emer
    -0.69
    Scient
    -0.68
    variable
    -0.68
    quant
    -0.67
    productive
    -0.67
    bodied
    -0.67
    POSITIVE LOGITS
    eering
    0.92
    Cand
    0.86
     Voters
    0.84
     primaries
    0.83
     runoff
    0.83
     turnout
    0.83
     caucuses
    0.80
     voters
    0.79
    legates
    0.78
     Caucus
    0.77
    Activations Density 0.195%

    No Known Activations