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

    Neuronpedia

    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. 2-RES-JB
    11. 17450
    Prev
    Next
    INDEX
    Explanations

    information related to survey polls and results

    oai_token-act-pair · gpt-3.5-turbo

    data concerning demographic polls and survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RIP
    -0.79
    æł
    -0.76
    RAW
    -0.71
    ufact
    -0.70
    forth
    -0.69
     airst
    -0.68
     ker
    -0.67
    hai
    -0.66
     Prol
    -0.65
     rein
    -0.64
    POSITIVE LOGITS
     surveyed
    1.08
     respondents
    1.04
     census
    0.90
     Gallup
    0.90
     Nielsen
    0.89
     demographics
    0.89
     demographic
    0.89
     polled
    0.88
     Census
    0.87
     surveys
    0.87
    Activations Density 0.759%

    No Known Activations