© 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. 3-RES-JB
    11. 4268
    Prev
    Next
    INDEX
    Explanations

    information related to public opinion polls and approval ratings

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to public opinion polls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.80
    RIP
    -0.78
    hod
    -0.76
    aundering
    -0.74
    EngineDebug
    -0.71
    ãĤ´ãĥ³
    -0.71
    mone
    -0.69
    orage
    -0.69
    unct
    -0.69
    initialized
    -0.67
    POSITIVE LOGITS
     polled
    1.24
     surveyed
    1.13
     Gallup
    1.06
     respondents
    1.06
     independents
    1.04
     undecided
    0.99
     voters
    0.98
     polls
    0.95
     demographics
    0.92
     percentages
    0.91
    Activations Density 0.754%

    No Known Activations