© 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. 13795
    Prev
    Next
    INDEX
    Explanations

    references to moving or transitioning from one state or condition to another

    oai_token-act-pair · gpt-3.5-turbo

    elements related to measurement and evaluation

    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
     Honour
    -0.56
    izoph
    -0.56
    %:
    -0.54
    .",
    -0.54
    &&
    -0.52
    eda
    -0.50
     Suppose
    -0.49
     differe
    -0.49
    ');
    -0.49
    ";
    -0.48
    POSITIVE LOGITS
     to
    0.86
     onto
    0.81
     back
    0.73
     into
    0.72
     directly
    0.69
     toward
    0.68
     toget
    0.68
     squarely
    0.60
    ãĥĺ
    0.57
     exclusively
    0.57
    Activations Density 0.336%

    No Known Activations