Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22452
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and political decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "voted."

    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
    ebin
    -0.78
    clair
    -0.76
    illin
    -0.75
    ptoms
    -0.75
    fal
    -0.72
    DragonMagazine
    -0.70
    qv
    -0.70
    uras
    -0.70
    vern
    -0.69
    ology
    -0.68
    POSITIVE LOGITS
     unanimously
    0.93
    room
    0.75
     overwhelmingly
    0.75
    ndum
    0.74
     YES
    0.73
     Leave
    0.73
     differently
    0.72
     against
    0.72
     blindly
    0.69
     Audit
    0.69
    Activations Density 0.027%

    No Known Activations