© 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. 8-RES-JB
    11. 24505
    Prev
    Next
    INDEX
    Explanations

    events or accidents leading to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    events involving injury or physical trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uniqueness
    -0.71
     approvals
    -0.67
     sincerity
    -0.66
     synergy
    -0.66
     specificity
    -0.64
    sense
    -0.64
     distinctions
    -0.64
     enthusiasm
    -0.63
     compliments
    -0.63
     informative
    -0.62
    POSITIVE LOGITS
     hanged
    1.09
     starve
    1.02
     unable
    0.99
     perished
    0.98
     drowned
    0.96
     euth
    0.94
     fled
    0.94
     plunged
    0.92
     plummet
    0.92
     perish
    0.91
    Activations Density 0.558%

    No Known Activations