© 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. 10-RES-JB
    11. 20346
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings like "Coroners" or titles that contain "Cor" followed by another letter

    oai_token-act-pair · gpt-3.5-turbo

    words associated with coroner or forensic investigation terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.68
    ndra
    -0.66
     srfAttach
    -0.64
     unbeliev
    -0.58
    mint
    -0.56
    iazep
    -0.56
     Principles
    -0.56
     pas
    -0.55
    ufact
    -0.54
    solid
    -0.54
    POSITIVE LOGITS
     Rasm
    0.79
    Ķ
    0.75
    INAL
    0.75
    etary
    0.70
     Janeiro
    0.69
    crew
    0.69
    ado
    0.69
    oreal
    0.69
    ij士
    0.64
    ¬
    0.64
    Activations Density 0.043%

    No Known Activations