© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    numerical descriptions or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "one," emphasizing individuality or singularity in various contexts

    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
    }:
    -0.68
    ographics
    -0.66
    urations
    -0.65
    ories
    -0.65
    ordes
    -0.63
    gif
    -0.63
    ocal
    -0.62
    oho
    -0.60
    chid
    -0.60
    inate
    -0.60
    POSITIVE LOGITS
     whereby
    0.85
     wherein
    0.84
     which
    0.81
     requiring
    0.78
     that
    0.77
     where
    0.77
    cknowled
    0.77
     hundred
    0.76
     whose
    0.76
     resembling
    0.75
    Activations Density 0.077%

    No Known Activations