© 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. 16080
    Prev
    Next
    INDEX
    Explanations

    reports of negative events or incidents related to accidents, shootings, attacks, or incidents resulting in harm or casualties

    oai_token-act-pair · gpt-3.5-turbo

    instances of incidents or events that involve violence or tragedy

    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
    bern
    -0.79
    peak
    -0.73
     representations
    -0.69
     persuasion
    -0.67
     endorsements
    -0.65
     notation
    -0.65
    unts
    -0.64
     introductory
    -0.64
    '/
    -0.64
    doms
    -0.63
    POSITIVE LOGITS
     occurred
    1.53
     caused
    1.41
     resulted
    1.37
     happened
    1.25
     sparked
    1.24
     transpired
    1.15
     rocked
    1.13
     prompted
    1.13
     erupted
    1.13
     worsened
    1.11
    Activations Density 0.270%

    No Known Activations