© 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. 8-RES-JB
    11. 11468
    Prev
    Next
    INDEX
    Explanations

    links or references to external stories or articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of articles and stories to share or email

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maid
    -0.67
    cedented
    -0.64
    ibles
    -0.60
     shred
    -0.60
    hib
    -0.59
     Surprise
    -0.59
    fed
    -0.58
     Ow
    -0.58
    heimer
    -0.57
    DERR
    -0.56
    POSITIVE LOGITS
    illian
    0.69
    20439
    0.69
     âĿ
    0.65
    ilitary
    0.64
    hei
    0.64
    raine
    0.63
    atis
    0.63
    ãĥĨãĤ£
    0.62
    olan
    0.61
    enaries
    0.60
    Activations Density 0.066%

    No Known Activations