© 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. 11-RES-JB
    11. 20386
    Prev
    Next
    INDEX
    Explanations

    athlete statistics, such as heights and weights

    oai_token-act-pair · gpt-3.5-turbo

    numerical and statistical data, particularly related to scoring or performance metrics

    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
    EMP
    -0.73
    ney
    -0.69
    ispers
    -0.65
     Noon
    -0.64
    amer
    -0.62
    \<
    -0.62
     territ
    -0.62
    aden
    -0.61
     telev
    -0.61
     examiner
    -0.60
    POSITIVE LOGITS
     195
    1.75
     210
    1.74
     205
    1.72
     235
    1.71
     215
    1.71
     245
    1.71
     203
    1.71
     202
    1.69
     241
    1.69
     208
    1.68
    Activations Density 0.181%

    No Known Activations