© 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. 6-RES-JB
    11. 7069
    Prev
    Next
    INDEX
    Explanations

    instances of the term "gerrymandering"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gerrymandering" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hander
    -0.68
    RP
    -0.67
    cliffe
    -0.65
    Ô
    -0.63
     tremend
    -0.61
    flash
    -0.60
    lik
    -0.60
    PAC
    -0.60
    FI
    -0.59
    AUD
    -0.59
    POSITIVE LOGITS
    obiles
    0.85
    usters
    0.79
    agog
    0.73
    ioxide
    0.72
    reprene
    0.72
    itiveness
    0.72
    obile
    0.71
    ards
    0.70
    Ŀ
    0.70
    ecake
    0.68
    Activations Density 0.178%

    No Known Activations