© 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. 9-RES-JB
    11. 11325
    Prev
    Next
    INDEX
    Explanations

    verb forms related to making threats

    oai_token-act-pair · gpt-3.5-turbo

    instances of threats or threatening behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gart
    -1.01
    angles
    -0.81
    mys
    -0.80
    gae
    -0.78
    æ©Ł
    -0.76
    coat
    -0.76
    olds
    -0.75
    rite
    -0.74
    tein
    -0.73
    cise
    -0.71
    POSITIVE LOGITS
     retaliation
    0.99
     retribution
    0.89
     repr
    0.87
     annihilation
    0.86
    lessly
    0.80
     eviction
    0.79
     violence
    0.75
     expulsion
    0.74
     termination
    0.74
     suicide
    0.73
    Activations Density 0.045%

    No Known Activations