© 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. 24216
    Prev
    Next
    INDEX
    Explanations

    mentions of magazine issues or editions

    oai_token-act-pair · gpt-3.5-turbo

    references to magazine or publication issues

    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
    raltar
    -0.81
    heed
    -0.77
    rophic
    -0.77
    tsky
    -0.77
    sing
    -0.76
    bones
    -0.74
    eric
    -0.72
     imperson
    -0.70
    ensions
    -0.68
    rous
    -0.67
    POSITIVE LOGITS
     thereof
    0.85
     Comics
    0.82
     Torrent
    0.71
     Comic
    0.69
     reprint
    0.66
    Issue
    0.66
     Valiant
    0.65
     Editors
    0.65
    ials
    0.63
    Journal
    0.63
    Activations Density 0.032%

    No Known Activations