© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 20354
    Prev
    Next
    INDEX
    Explanations

    nouns related to competitions and physical objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weight classes and physical attributes in sports and health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.81
    rawdownloadcloneembedreportprint
    -0.78
    alys
    -0.77
    æ©
    -0.75
    iless
    -0.75
    beer
    -0.74
    canon
    -0.72
    baugh
    -0.71
    igious
    -0.70
    é¾įå¥ij士
    -0.70
    POSITIVE LOGITS
     finalists
    0.69
     deployments
    0.67
     movement
    0.66
     nominees
    0.64
     procession
    0.63
     nominee
    0.62
     entrants
    0.62
     candidates
    0.61
     hybrids
    0.61
     succession
    0.61
    Activations Density 0.549%

    No Known Activations