© 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. 0-RES-JB
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    mentioned of individuals who have passed away

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "died" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Integration
    -0.59
     leverage
    -0.58
     targeting
    -0.58
     pursuit
    -0.57
     tack
    -0.57
     competitiveness
    -0.56
     flexibility
    -0.56
     CONC
    -0.56
     Open
    -0.54
     Imag
    -0.54
    POSITIVE LOGITS
     died
    3.75
     perished
    2.74
     dies
    2.51
     Died
    2.36
     die
    2.10
     succumbed
    1.97
     survived
    1.88
     drowned
    1.78
     killed
    1.73
     dying
    1.68
    Activations Density 0.024%

    No Known Activations