© 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. 7308
    Prev
    Next
    INDEX
    Explanations

    words related to physical damage and harm

    oai_token-act-pair · gpt-3.5-turbo

    references to physical damage

    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
    ramid
    -0.69
    zee
    -0.68
    KER
    -0.67
    tre
    -0.66
    liner
    -0.65
    rams
    -0.64
    zsche
    -0.64
     Valhalla
    -0.63
    arte
    -0.63
    Tri
    -0.63
    POSITIVE LOGITS
     inflicted
    1.08
     damage
    1.07
    damage
    0.89
     mitigation
    0.88
     damaged
    0.83
     damages
    0.79
     wrought
    0.78
     psychiat
    0.78
     havoc
    0.78
     horm
    0.76
    Activations Density 0.019%

    No Known Activations