© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10301
    Prev
    Next
    INDEX
    Explanations

    words related to names starting with "B" or involving the letter "B"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "a" and its frequency in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pter
    -0.66
    uania
    -0.65
    oxide
    -0.65
     Sorce
    -0.64
    igraph
    -0.63
    advertisement
    -0.62
    inav
    -0.61
     eas
    -0.61
    vp
    -0.60
     showc
    -0.60
    POSITIVE LOGITS
    wana
    0.95
    lehem
    0.91
    aneers
    0.83
    levard
    0.83
    oola
    0.78
    leck
    0.77
    abase
    0.77
    reau
    0.77
     Ferry
    0.76
    EStreamFrame
    0.76
    Activations Density 0.329%

    No Known Activations