© 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. 9-RES-JB
    11. 20758
    Prev
    Next
    INDEX
    Explanations

    words related to physical injury, particularly stabbings

    oai_token-act-pair · gpt-3.5-turbo

    references to stabbings or knife-related injuries

    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
    -0.85
    zeb
    -0.84
    anamo
    -0.76
    ayson
    -0.75
    amina
    -0.72
    usk
    -0.70
    cules
    -0.68
    ained
    -0.68
    oses
    -0.66
    umen
    -0.65
    POSITIVE LOGITS
    lished
    0.91
    ritch
    0.74
    rers
    0.74
    ival
    0.73
    ¾
    0.71
    ¼
    0.71
    nesday
    0.70
    hold
    0.70
    ters
    0.69
    TERN
    0.68
    Activations Density 0.105%

    No Known Activations