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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24041
    Prev
    Next
    INDEX
    Explanations

    references to fatal events and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fatal" related to events or outcomes

    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
    annis
    -0.83
    orthy
    -0.75
    arity
    -0.73
    arte
    -0.73
    sheets
    -0.69
    PT
    -0.69
    sheet
    -0.68
    ebook
    -0.68
    berman
    -0.68
    arta
    -0.68
    POSITIVE LOGITS
     fatal
    1.09
    istically
    1.04
    istic
    1.00
     flaw
    0.85
    ities
    0.84
     stabbing
    0.80
    ism
    0.80
    ãĥ¥
    0.80
     fatally
    0.79
    ized
    0.78
    Activations Density 0.006%

    No Known Activations