© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 16525
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or commands directing to specific websites or actions

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts to take specific actions or navigate to links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminishing
    -0.64
    qqa
    -0.63
    stood
    -0.60
    ariat
    -0.60
     retaining
    -0.58
    ÏĦ
    -0.58
     sil
    -0.57
    ulating
    -0.54
    ament
    -0.54
    plom
    -0.54
    POSITIVE LOGITS
     HERE
    0.98
    ogly
    0.86
    quartered
    0.84
     ahead
    0.83
    ethe
    0.83
    ggle
    0.78
    lly
    0.77
    og
    0.76
     Subscribe
    0.75
     download
    0.75
    Activations Density 0.055%

    No Known Activations