© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    words related to parliamentary and political settings, specifically focusing on party members

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ben" and related terms

    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
     Kinnikuman
    -0.83
    earable
    -0.74
    matic
    -0.68
    herry
    -0.68
    mble
    -0.66
    inarily
    -0.66
     Pione
    -0.64
     abundance
    -0.64
    displayText
    -0.63
    UGC
    -0.63
    POSITIVE LOGITS
    jamin
    1.69
    ben
    1.05
    ghazi
    1.03
    nington
    0.90
    acon
    0.89
    stein
    0.86
    oit
    0.85
    hart
    0.85
    chers
    0.85
    utz
    0.82
    Activations Density 0.008%

    No Known Activations