© 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. 24109
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Hammond"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, particularly those related to prominent cases or events

    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
    atively
    -0.83
    apult
    -0.82
    coni
    -0.78
    roleum
    -0.78
    geries
    -0.75
    ologies
    -0.74
    ozo
    -0.73
    oday
    -0.73
    aundering
    -0.72
    que
    -0.71
    POSITIVE LOGITS
    sburg
    1.11
    shire
    1.10
    s
    1.07
    sf
    0.74
     wip
    0.73
    swer
    0.72
    sb
    0.71
    sie
    0.70
    spr
    0.69
    rontal
    0.68
    Activations Density 0.117%

    No Known Activations