© 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. 13834
    Prev
    Next
    INDEX
    Explanations

    specific names in a text

    oai_token-act-pair · gpt-3.5-turbo

    specific names, terms, or identifiers within a context

    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
    pter
    -0.76
    isSpecialOrderable
    -0.66
    vp
    -0.65
    ĸļ
    -0.63
     vide
    -0.61
    repeat
    -0.61
    wives
    -0.59
    eln
    -0.56
    lance
    -0.56
    ngth
    -0.55
    POSITIVE LOGITS
    lehem
    0.78
    acci
    0.77
     Beaut
    0.76
    emouth
    0.73
     Aires
    0.69
    swick
    0.67
    illet
    0.67
    liga
    0.66
    abase
    0.66
    apest
    0.65
    Activations Density 0.252%

    No Known Activations