© 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. 6-RES-JB
    11. 17404
    Prev
    Next
    INDEX
    Explanations

    words related to physical torture and abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.84
    ership
    -0.75
     explan
    -0.65
     iod
    -0.64
     lender
    -0.64
    nect
    -0.64
    ijk
    -0.63
    arger
    -0.62
    ouver
    -0.61
    soDeliveryDate
    -0.61
    POSITIVE LOGITS
     torture
    0.91
    imony
    0.79
    urous
    0.78
     tortured
    0.74
    rs
    0.72
     captives
    0.72
    APE
    0.71
     ABE
    0.70
    rers
    0.70
     confinement
    0.67
    Activations Density 0.025%

    No Known Activations