© 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. 6-RES-JB
    11. 18426
    Prev
    Next
    INDEX
    Explanations

    words related to events and gathering of people

    oai_token-act-pair · gpt-3.5-turbo

    terms related to attendance and voter turnout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thodox
    -0.74
    thur
    -0.73
    nered
    -0.68
    olog
    -0.67
    enegger
    -0.66
    sonian
    -0.65
     pity
    -0.63
    esthetic
    -0.63
    TIT
    -0.62
    grave
    -0.61
    POSITIVE LOGITS
     rates
    0.80
     attendance
    0.80
     rate
    0.78
    enance
    0.76
     turnout
    0.72
     Attend
    0.69
     Rates
    0.67
     rolls
    0.67
     tickets
    0.65
    aho
    0.65
    Activations Density 0.066%

    No Known Activations