© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 15881
    Prev
    Next
    INDEX
    Explanations

    words related to intense vocal expressions, specifically screaming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scream" or its variations in various contexts of urgency or emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilege
    -0.91
    omaly
    -0.82
    Arthur
    -0.78
    inion
    -0.71
    folios
    -0.70
    rost
    -0.68
     Cheong
    -0.64
    pend
    -0.64
    ajo
    -0.64
    insula
    -0.64
    POSITIVE LOGITS
     louder
    1.00
     screamed
    0.96
     scream
    0.91
     screaming
    0.90
     screams
    0.87
     aloud
    0.87
     Scream
    0.83
     loudly
    0.82
     begging
    0.79
    ingly
    0.77
    Activations Density 0.022%

    No Known Activations