© 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. 18871
    Prev
    Next
    INDEX
    Explanations

    news-related phrases or headlines that include numbers or dates

    oai_token-act-pair · gpt-3.5-turbo

    recommendations or highlights of important videos and stories

    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
    ©¶æ
    -0.78
    everal
    -0.70
    SHARE
    -0.68
    DEN
    -0.67
    ailability
    -0.65
    ccording
    -0.63
    ĸļ
    -0.62
     Kaiser
    -0.60
     Nanto
    -0.58
    ŃĶ
    -0.57
    POSITIVE LOGITS
     foul
    0.62
     annex
    0.59
     aven
    0.55
     charge
    0.55
     warn
    0.54
     bass
    0.54
     slay
    0.53
     die
    0.52
    odon
    0.52
     board
    0.52
    Activations Density 0.088%

    No Known Activations