© 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 EvalsExportsinterp-engineNEWAPI 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. 11348
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation and wings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wing" and its variations

    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
     Cumber
    -0.81
     Uz
    -0.71
    ãĥ¤
    -0.71
     Scotia
    -0.70
     Glock
    -0.69
     Tycoon
    -0.64
     Shinzo
    -0.63
     Obj
    -0.62
     Nare
    -0.62
     CBI
    -0.62
    POSITIVE LOGITS
    tip
    1.49
    nuts
    1.39
    nut
    1.36
    tips
    1.30
    edly
    1.12
    pan
    1.03
    bill
    1.02
     Chun
    0.96
    mares
    0.93
    pread
    0.93
    Activations Density 0.040%

    No Known Activations