© 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. 11-RES-JB
    11. 443
    Prev
    Next
    INDEX
    Explanations

    terms related to technical details, projects, and developments

    oai_token-act-pair · gpt-3.5-turbo
    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
    ":"/
    -0.69
    iku
    -0.64
    ptions
    -0.62
    ãĤ¨ãĥ«
    -0.62
    gression
    -0.59
    Either
    -0.58
    è£ħ
    -0.57
    enda
    -0.57
    к
    -0.57
     ¯
    -0.56
    POSITIVE LOGITS
     etc
    1.38
     and
    1.30
    etc
    0.86
     plus
    0.83
    and
    0.82
     AND
    0.73
     &
    0.70
     or
    0.66
     et
    0.62
     respectively
    0.59
    Activations Density 0.408%

    No Known Activations