© 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. 11-RES-JB
    11. 2536
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations or specifically Quebec

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Quebec and related cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsky
    -0.74
    FORE
    -0.71
    bilt
    -0.70
    lihood
    -0.65
    nces
    -0.63
    WAYS
    -0.62
    >>>>>>>>
    -0.61
    ptive
    -0.57
    ctory
    -0.56
    mbol
    -0.55
    POSITIVE LOGITS
    ed
    1.44
    er
    1.16
    s
    1.12
    ing
    1.10
    ive
    1.08
    ion
    1.05
    edly
    1.05
    ile
    1.03
    ic
    1.03
    iles
    0.99
    Activations Density 0.338%

    No Known Activations