© 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. 9-RES-JB
    11. 16557
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'Virgin' with a relatively high activation level

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Virgin 2"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kson
    -0.91
    ovie
    -0.79
    itsch
    -0.72
    govtrack
    -0.70
    bered
    -0.68
    ptin
    -0.66
    aching
    -0.64
    iggurat
    -0.64
    pter
    -0.64
    selves
    -0.62
    POSITIVE LOGITS
     Islands
    1.03
     Galactic
    0.95
    ity
    0.93
     Virgin
    0.91
    Virgin
    0.90
    ian
    0.85
    ienne
    0.81
    ius
    0.81
    itas
    0.80
     pigeon
    0.79
    Activations Density 0.028%

    No Known Activations