© 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. 10-RES-JB
    11. 11258
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to Chicago

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regress
    -0.64
     dividend
    -0.63
    schild
    -0.61
    MENT
    -0.60
    WARD
    -0.58
     revelation
    -0.58
     tert
    -0.57
     respects
    -0.57
     Scythe
    -0.56
     neut
    -0.56
    POSITIVE LOGITS
    oga
    0.92
    oland
    0.82
    uan
    0.77
    oen
    0.76
    ulhu
    0.76
    otta
    0.74
    atti
    0.73
    ega
    0.72
    ractor
    0.72
    amac
    0.71
    Activations Density 0.100%

    No Known Activations