© 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. 11-RES-JB
    11. 22671
    Prev
    Next
    INDEX
    Explanations

    names containing the pattern "ane" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cane" and its variations

    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
    s
    -0.85
    rador
    -0.75
    spring
    -0.72
    sburgh
    -0.71
    dogs
    -0.69
    andise
    -0.67
    lishes
    -0.66
    said
    -0.66
    achusetts
    -0.64
    orate
    -0.64
    POSITIVE LOGITS
    hyde
    1.08
    jad
    0.95
    cki
    0.94
    gas
    0.91
    cker
    0.82
    agle
    0.82
    ck
    0.81
    vil
    0.79
    resp
    0.78
    utral
    0.78
    Activations Density 0.075%

    No Known Activations