© 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. 4-RES-JB
    11. 9549
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals who have died

    oai_token-act-pair · gpt-3.5-turbo

    references to death

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

    No Comments

    Negative Logits
    rouse
    -0.77
    Allen
    -0.74
    wcsstore
    -0.71
    arel
    -0.67
    OR
    -0.66
    OPER
    -0.66
    arist
    -0.66
    orers
    -0.64
    Grab
    -0.64
    orney
    -0.64
    POSITIVE LOGITS
     horribly
    0.97
     tragically
    0.81
    zai
    0.79
     toll
    0.79
    uary
    0.79
    ffen
    0.79
     intest
    0.78
     peacefully
    0.77
    itial
    0.73
     miser
    0.73
    Activations Density 0.025%

    No Known Activations