© 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. 2-RES-JB
    11. 469
    Prev
    Next
    INDEX
    Explanations

    the word 'choke'

    oai_token-act-pair · gpt-4-turbo

    words related to physical acts of constriction or restriction

    oai_token-act-pair · gpt-3.5-turbo

    references to choking or asphyxiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CTV
    -0.72
    algia
    -0.69
    elf
    -0.67
    ocent
    -0.67
    arians
    -0.66
    igation
    -0.66
    CV
    -0.65
    abol
    -0.64
    UTC
    -0.64
    atri
    -0.64
    POSITIVE LOGITS
     choke
    1.05
     choked
    1.03
     choking
    0.99
    leneck
    0.88
     throat
    0.78
     necks
    0.78
    bowl
    0.76
    weed
    0.75
     cane
    0.74
    puff
    0.72
    Activations Density 0.007%

    No Known Activations