© 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. 1-RES-JB
    11. 20336
    Prev
    Next
    INDEX
    Explanations

    descriptive action verbs related to physical gestures

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions or gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inval
    -0.73
    Gas
    -0.63
     decre
    -0.63
     outlandish
    -0.63
    feat
    -0.62
     insanity
    -0.62
     banned
    -0.62
    Haunted
    -0.61
     outlawed
    -0.61
     libel
    -0.60
    POSITIVE LOGITS
    ersen
    0.83
    amples
    0.81
    imester
    0.81
    ngth
    0.80
    ategory
    0.78
    selage
    0.78
    aturated
    0.78
    ivari
    0.77
    verty
    0.75
    rame
    0.74
    Activations Density 0.000%

    No Known Activations