© 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. 20967
    Prev
    Next
    INDEX
    Explanations

    references to specific versions of Ubuntu operating system

    oai_token-act-pair · gpt-3.5-turbo

    specific version numbers and update details related to software, particularly Ubuntu

    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
     Bucks
    -0.59
    ammed
    -0.59
     autobiography
    -0.57
     Bolton
    -0.57
     affili
    -0.56
     Polo
    -0.56
     Bots
    -0.56
     transact
    -0.56
     tert
    -0.55
     bom
    -0.54
    POSITIVE LOGITS
    04
    1.13
    0
    0.92
    02
    0.89
    01
    0.88
    05
    0.87
    é¾įå¥ij士
    0.87
    10
    0.86
    06
    0.84
    1
    0.84
    03
    0.82
    Activations Density 0.032%

    No Known Activations