© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 17625
    Prev
    Next
    INDEX
    Explanations

    instances of words related to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zee
    -0.77
    zees
    -0.76
    avanaugh
    -0.71
    ullivan
    -0.71
    rows
    -0.71
    ILE
    -0.71
    @@@@
    -0.69
    itudes
    -0.66
    ģĸ
    -0.66
    ihu
    -0.66
    POSITIVE LOGITS
     prevention
    0.92
     inflicted
    0.91
     injury
    0.89
     incurred
    0.84
     prone
    0.82
     replacements
    0.82
     injuries
    0.80
     suffered
    0.79
     riddled
    0.79
     plagued
    0.78
    Activations Density 0.027%

    No Known Activations