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. 0-RES-JB
    6. 24385
    Prev
    Next
    INDEX
    Explanations

    references to the polling organization "Gallup" in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of polling organizations and surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoil
    -0.77
     tender
    -0.68
     spo
    -0.66
     blades
    -0.65
    Fi
    -0.64
    master
    -0.60
     licence
    -0.60
     armour
    -0.60
    scar
    -0.60
    ruction
    -0.60
    POSITIVE LOGITS
     Gallup
    4.11
     Pew
    1.69
    Gall
    1.60
     Rasmussen
    1.52
     Billboard
    1.19
     polls
    1.18
     Newsweek
    1.16
     polling
    1.16
     Ips
    1.16
     Brookings
    1.15
    Activations Density 0.012%

    No Known Activations