© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12840
    Prev
    Next
    INDEX
    Explanations

    mentions of formal voting or approval processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of voting actions or decisions made by official bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clair
    -0.76
    fal
    -0.74
    ptoms
    -0.73
    spr
    -0.71
    antha
    -0.71
    iasis
    -0.70
    xia
    -0.70
    jiang
    -0.67
    ebin
    -0.67
    elope
    -0.65
    POSITIVE LOGITS
     unanimously
    1.38
     overwhelmingly
    1.03
     favorably
    0.92
     decisively
    0.90
     against
    0.90
     differently
    0.84
     approving
    0.84
     accordingly
    0.77
     wisely
    0.75
     positively
    0.74
    Activations Density 0.040%

    No Known Activations