© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    the word "Bah" at varied activations

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to individuals or entities with the prefix "Bah" or "Bhar."

    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
    ographically
    -0.71
    ographed
    -0.69
    ographer
    -0.65
    essee
    -0.64
     Grave
    -0.64
    ilver
    -0.63
    ographic
    -0.62
    ographers
    -0.61
    ffic
    -0.61
    pelling
    -0.61
    POSITIVE LOGITS
    SourceFile
    0.86
    TeX
    0.82
    ls
    0.82
    ucha
    0.81
    aii
    0.81
    aha
    0.81
    nam
    0.80
    aban
    0.79
    rief
    0.78
    abus
    0.77
    Activations Density 0.079%

    No Known Activations