Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7853
    Prev
    Next
    INDEX
    Explanations

    references to the concept of death

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "death" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECA
    -0.78
    Cola
    -0.72
    MN
    -0.71
    CN
    -0.69
    OPER
    -0.68
    TRY
    -0.68
     CLIENT
    -0.68
    æ©Ł
    -0.67
    RECT
    -0.66
    ATIONS
    -0.66
    POSITIVE LOGITS
    blow
    1.17
    stroke
    1.11
     toll
    1.08
    match
    1.04
    trap
    0.99
    adder
    0.97
    claw
    0.97
     thro
    0.97
    guard
    0.96
    touch
    0.93
    Activations Density 0.049%

    No Known Activations