© 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. 1-RES-JB
    11. 12820
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the abbreviation "bo"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.81
    UAL
    -0.76
     recess
    -0.67
    代
    -0.66
    OPE
    -0.64
    ATIONAL
    -0.63
     Pwr
    -0.63
     discriminating
    -0.63
    IDENT
    -0.62
    istant
    -0.61
    POSITIVE LOGITS
    olean
    1.39
    bo
    1.15
    oru
    0.95
    gey
    0.94
    zz
    0.91
     Bagg
    0.91
    leans
    0.89
     Bo
    0.89
    oons
    0.86
    hari
    0.84
    Activations Density 0.004%

    No Known Activations