© 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. 1-RES-JB
    11. 24244
    Prev
    Next
    INDEX
    Explanations

    matches between two entities or teams

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "vs" (versus) phrase, indicating a competitive or comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    collar
    -0.84
    irlf
    -0.73
     liner
    -0.72
    lene
    -0.71
    ERN
    -0.71
    lus
    -0.71
    olitan
    -0.68
    mberg
    -0.66
    affected
    -0.66
    DragonMagazine
    -0.66
    POSITIVE LOGITS
     vs
    0.81
     situational
    0.69
     Vs
    0.66
     ponder
    0.65
    vs
    0.63
     lbs
    0.62
     huh
    0.62
    .,
    0.61
     Zombies
    0.60
     versus
    0.60
    Activations Density 0.006%

    No Known Activations