© 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. 8-RES-JB
    11. 17656
    Prev
    Next
    INDEX
    Explanations

    terms related to severe physical harm or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "badly" and its variations indicating negative conditions or situations

    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
    uality
    -0.88
    heny
    -0.74
    atu
    -0.74
    itivity
    -0.74
     Parenthood
    -0.73
     paternity
    -0.71
     Citation
    -0.70
    itures
    -0.69
    iture
    -0.69
    cript
    -0.68
    POSITIVE LOGITS
     beaten
    0.96
     wounded
    0.93
     lacking
    0.93
     mistaken
    0.93
     damaged
    0.90
     bruised
    0.89
     outnumbered
    0.88
     poisoned
    0.87
    needed
    0.87
     injured
    0.87
    Activations Density 0.054%

    No Known Activations