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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17363
    Prev
    Next
    INDEX
    Explanations

    mentions of flea markets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fleas

    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
    LESS
    -0.85
    raint
    -0.68
    quickShipAvailable
    -0.66
     Sinclair
    -0.65
     dedication
    -0.65
    Demand
    -0.58
    OUNT
    -0.58
    lain
    -0.57
    osuke
    -0.56
     Nadu
    -0.55
    POSITIVE LOGITS
    cks
    1.14
    uve
    1.07
    ischer
    0.97
    mington
    0.94
    ck
    0.93
    xt
    0.90
    ener
    0.89
    anut
    0.89
    ername
    0.88
    llo
    0.86
    Activations Density 0.030%

    No Known Activations