© 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. 10-RES-JB
    11. 19056
    Prev
    Next
    INDEX
    Explanations

    keywords related to the technology industry

    oai_token-act-pair · gpt-3.5-turbo

    references to the technology industry and related companies

    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
    theless
    -0.74
     Bolton
    -0.73
    lihood
    -0.72
     Chamberlain
    -0.72
     Hodg
    -0.71
     Technique
    -0.69
     Maurit
    -0.63
     Wem
    -0.63
     Twain
    -0.63
     Cruel
    -0.62
    POSITIVE LOGITS
    Crunch
    1.33
     savvy
    1.06
    sav
    1.04
    stars
    0.94
    sector
    0.92
    speak
    0.87
     specs
    0.86
     startups
    0.86
    onomy
    0.84
     giants
    0.83
    Activations Density 0.035%

    No Known Activations