© 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. 8-RES-JB
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    it references to estimated numerical values

    oai_token-act-pair · gpt-3.5-turbo

    quantitative estimates or projections related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kelvin
    -0.65
     Dak
    -0.64
    ierre
    -0.63
    isons
    -0.61
    beta
    -0.61
    nesday
    -0.59
     reminded
    -0.58
    bert
    -0.58
    always
    -0.58
    ibilities
    -0.57
    POSITIVE LOGITS
     TOTAL
    0.95
    %"
    0.83
     approximately
    0.81
     ballpark
    0.80
     total
    0.79
     roughly
    0.77
     aver
    0.77
    gross
    0.75
    cffff
    0.75
     underestimate
    0.74
    Activations Density 0.267%

    No Known Activations