© 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. 11-RES-JB
    11. 19726
    Prev
    Next
    INDEX
    Explanations

    words related to curvature or shape

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "curb."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.69
    enger
    -0.63
     Live
    -0.62
     prest
    -0.61
     Remem
    -0.60
     mant
    -0.59
     Shining
    -0.57
     McKenna
    -0.57
     Spice
    -0.57
     worst
    -0.57
    POSITIVE LOGITS
    tailed
    1.38
    tesy
    1.31
    mud
    1.30
    ried
    1.19
    ving
    1.16
    vy
    1.14
    iosity
    1.13
    rier
    1.12
    rying
    1.12
    tsy
    1.12
    Activations Density 0.021%

    No Known Activations