© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8548
    Prev
    Next
    INDEX
    Explanations

    numerical values related to a specific identifier or version

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 14 with varied contexts

    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
    oyd
    -0.82
    atem
    -0.77
    omial
    -0.65
    ows
    -0.62
    ingham
    -0.61
    ãĤ¡
    -0.61
    ation
    -0.61
     Laden
    -0.61
    ogue
    -0.60
     Beckham
    -0.60
    POSITIVE LOGITS
    00
    1.07
    393
    1.03
    06
    1.03
    08
    1.02
    09
    0.99
    07
    0.97
    03
    0.95
    92
    0.95
    02
    0.95
    04
    0.94
    Activations Density 0.079%

    No Known Activations