© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19317
    Prev
    Next
    INDEX
    Explanations

    information related to public opinion surveys and statistics

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" followed by percentages or statistics related to public opinion

    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
    artifacts
    -0.71
    fork
    -0.68
    ucci
    -0.67
    pedia
    -0.66
    acha
    -0.66
    print
    -0.65
    alph
    -0.64
    ollah
    -0.63
    arium
    -0.63
    âĺ
    -0.63
    POSITIVE LOGITS
     respondents
    1.42
     surveyed
    0.98
     voters
    0.98
     households
    0.94
     Americans
    0.93
     polled
    0.93
     participants
    0.92
     Britons
    0.90
     adults
    0.89
     responders
    0.88
    Activations Density 0.077%

    No Known Activations