© 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. 11-RES-JB
    11. 10062
    Prev
    Next
    INDEX
    Explanations

    references to polls conducted by news organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to polls and surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.75
    wikipedia
    -0.69
     forgiven
    -0.67
    displayText
    -0.65
    assetsadobe
    -0.63
     Paramount
    -0.61
     Commodore
    -0.60
    comed
    -0.59
     promoters
    -0.59
    udicrous
    -0.58
    POSITIVE LOGITS
     survey
    1.34
     poll
    1.32
     analysis
    1.09
     Poll
    1.07
    Poll
    1.05
     polling
    1.03
     surveys
    1.02
     Survey
    1.02
     study
    1.01
     Analytics
    0.97
    Activations Density 0.146%

    No Known Activations