© 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. 1-RES-JB
    11. 24112
    Prev
    Next
    INDEX
    Explanations

    terms related to political filibusters and medical blood clots

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legislative procedures and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ité
    -0.76
     Occ
    -0.76
    orp
    -0.75
    oke
    -0.74
    ology
    -0.73
    ramid
    -0.70
    ipal
    -0.68
    othermal
    -0.68
    elf
    -0.66
    ammad
    -0.66
    POSITIVE LOGITS
     filib
    1.41
     filibuster
    1.22
    usters
    0.80
    buster
    0.73
     lash
    0.70
     pauses
    0.68
     hearings
    0.68
     muster
    0.68
     dodging
    0.67
     clot
    0.67
    Activations Density 0.005%

    No Known Activations