© 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. 11-RES-JB
    11. 20826
    Prev
    Next
    INDEX
    Explanations

    dates in the format YYYY/MM/DD

    oai_token-act-pair · gpt-3.5-turbo

    links related to news articles and web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.83
    ÃŃs
    -0.66
     pione
    -0.63
     Crew
    -0.58
     bonding
    -0.57
     Sisters
    -0.56
     peaks
    -0.55
     este
    -0.55
     Cald
    -0.55
     Samp
    -0.53
    POSITIVE LOGITS
    /_
    1.54
    /
    1.48
    /?
    1.43
    /-
    1.33
    /)
    1.30
    /,
    1.29
    /#
    1.23
    /"
    1.19
    /.
    1.13
    \/
    1.12
    Activations Density 0.065%

    No Known Activations