© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a strong preference or insistence on a particular way of doing things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "this way."

    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
     livest
    -0.73
     sugg
    -0.73
    ynski
    -0.68
    urated
    -0.64
    usters
    -0.63
    erville
    -0.63
    oute
    -0.63
    ongo
    -0.63
    unts
    -0.62
    uster
    -0.62
    POSITIVE LOGITS
    forward
    0.79
    fare
    0.78
    ward
    0.76
    finding
    0.75
     Sabha
    0.75
    footed
    0.73
    zzo
    0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.67
    soever
    0.66
     forever
    0.64
    Activations Density 0.035%

    No Known Activations