© 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. 13984
    Prev
    Next
    INDEX
    Explanations

    things or actions that have never been experienced or encountered before

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "before" as an indicator of past experiences or comparisons

    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
    atana
    -0.75
    Ń
    -0.74
    ¥
    -0.66
    IJ
    -0.65
    ãĥ¼ãĥ
    -0.65
    à©
    -0.63
    kees
    -0.63
    etsy
    -0.63
    ©
    -0.63
    urther
    -0.62
    POSITIVE LOGITS
    .
    0.77
     except
    0.74
     âĢķ
    0.70
    ;
    0.68
    NetMessage
    0.67
     sunrise
    0.65
    !
    0.65
     disappearing
    0.65
    nn
    0.65
    empt
    0.62
    Activations Density 0.046%

    No Known Activations