© 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. 12-RES-JB
    11. 2836
    Prev
    Next
    INDEX
    Explanations

    medical conditions, locations, and personnel associated with medical reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of significant numerical values associated with statistics or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    hya
    -0.64
    hammad
    -0.61
    sterdam
    -0.59
     largeDownload
    -0.57
    fman
    -0.56
    agos
    -0.53
    INTON
    -0.53
    houses
    -0.52
    orsi
    -0.52
    cribed
    -0.51
    POSITIVE LOGITS
    line
    0.79
    ut
    0.68
    ately
    0.67
    ile
    0.65
    x
    0.62
    lu
    0.61
    lines
    0.61
    ificant
    0.60
    ate
    0.59
    oe
    0.58
    Activations Density 0.265%

    No Known Activations