© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16968
    Prev
    Next
    INDEX
    Explanations

    phrases prompting the reader to check out something

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging the reader to check out content or 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
     suscept
    -0.83
     reluct
    -0.68
    lishes
    -0.65
     mathemat
    -0.63
     inval
    -0.62
    cffffcc
    -0.61
    onte
    -0.59
    EStreamFrame
    -0.59
    OF
    -0.59
    ody
    -0.58
    POSITIVE LOGITS
    mate
    1.27
    lists
    1.01
     out
    1.00
    boxes
    0.97
    list
    0.92
    out
    0.92
    points
    0.87
    mates
    0.87
    outs
    0.85
    point
    0.78
    Activations Density 0.017%

    No Known Activations