© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sad" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo
    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
     sterling
    -0.69
     FANT
    -0.66
     platinum
    -0.63
    姫
    -0.63
     unde
    -0.63
     Reloaded
    -0.62
     pegged
    -0.61
     bottled
    -0.61
     Kendrick
    -0.60
     helic
    -0.59
    POSITIVE LOGITS
    omas
    1.20
    istic
    1.04
    hus
    1.01
    emic
    1.00
    amoto
    0.98
    hya
    0.98
    du
    0.96
    ness
    0.95
    ako
    0.95
    acio
    0.92
    Activations Density 0.039%

    No Known Activations