© 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. 3-RES-JB
    11. 1885
    Prev
    Next
    INDEX
    Explanations

    mentions of filibusters and related political terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative procedures and contentious political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orp
    -0.70
    ité
    -0.68
    Contract
    -0.68
     Occ
    -0.67
    ensual
    -0.67
    ramid
    -0.67
    aspers
    -0.65
    çīĪ
    -0.65
     Degree
    -0.64
    orporated
    -0.63
    POSITIVE LOGITS
     filib
    1.24
     filibuster
    1.17
     hearings
    0.81
    buster
    0.79
    usters
    0.73
     nominating
    0.71
     repeal
    0.69
    flower
    0.69
    vote
    0.68
    ignt
    0.68
    Activations Density 0.008%

    No Known Activations