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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20814
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the term "itch"

    oai_token-act-pair · gpt-3.5-turbo

    words associated with skin conditions or ailments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.80
    anguage
    -0.73
     behavi
    -0.73
    zac
    -0.69
    ragon
    -0.69
    icative
    -0.69
    terior
    -0.69
    omial
    -0.66
    agonist
    -0.65
    quished
    -0.64
    POSITIVE LOGITS
    imaru
    0.98
    fork
    0.91
    icago
    0.85
    IELD
    0.80
    itch
    0.74
    urch
    0.71
    aired
    0.70
    sburgh
    0.70
    roll
    0.68
    cock
    0.68
    Activations Density 0.048%

    No Known Activations