© 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. 9-RES-JB
    11. 20856
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rare or special opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.79
    ngth
    -0.69
    allo
    -0.67
    ĸļ
    -0.67
     Canaver
    -0.66
    bj
    -0.65
    retty
    -0.62
    wire
    -0.60
    hemy
    -0.60
    heit
    -0.58
    POSITIVE LOGITS
    \\\\\\\\
    0.59
    udes
    0.55
     Virtue
    0.50
     divide
    0.49
    urations
    0.48
     electricity
    0.47
    ations
    0.46
     stores
    0.45
     scope
    0.45
     ms
    0.45
    Activations Density 0.274%

    No Known Activations