© 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. 8-RES-JB
    11. 1222
    Prev
    Next
    INDEX
    Explanations

    keywords indicating important points or conclusions, often separated by colons

    oai_token-act-pair · gpt-3.5-turbo

    key findings or conclusions from reports

    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
     souven
    -0.77
     lett
    -0.74
     pilgr
    -0.71
     airs
    -0.70
     ceremony
    -0.68
    ãĥĺ
    -0.68
     tatt
    -0.66
     ceremon
    -0.65
     mosqu
    -0.65
     idols
    -0.65
    POSITIVE LOGITS
     methodological
    1.38
     empirical
    1.09
     statistical
    0.99
     statistically
    0.98
     conclusions
    0.98
     quantitative
    0.97
     empir
    0.96
    Evidence
    0.93
     policymakers
    0.93
     anecdotal
    0.91
    Activations Density 0.970%

    No Known Activations