© 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. 9-RES-JB
    11. 15846
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases with strong emotional connotations

    oai_token-act-pair · gpt-3.5-turbo

    single occurrences of various letters or symbols in the text

    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
     interacts
    -0.66
     Chao
    -0.64
    querque
    -0.62
     targ
    -0.62
     KS
    -0.61
     bake
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
    enhagen
    -0.60
     Decker
    -0.59
     Dres
    -0.59
    POSITIVE LOGITS
    seless
    1.03
    icious
    1.02
    bidden
    1.02
    ificantly
    0.99
    ateful
    0.99
    iscal
    0.97
    initely
    0.97
    usterity
    0.95
    actory
    0.95
    thora
    0.94
    Activations Density 0.210%

    No Known Activations