© 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. 22248
    Prev
    Next
    INDEX
    Explanations

    references to a person named Turner, with a particular focus on negative events or controversies involving him

    oai_token-act-pair · gpt-3.5-turbo

    references to the individual Brock Turner

    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
     scorp
    -0.77
     carc
    -0.68
    ++
    -0.68
    include
    -0.68
    Xi
    -0.65
     mail
    -0.65
    pas
    -0.64
     inbox
    -0.64
    âĢ¦..
    -0.63
    mails
    -0.62
    POSITIVE LOGITS
     Turner
    4.00
    Turn
    1.38
     Sinclair
    1.37
     Robertson
    1.28
     Stephenson
    1.16
     Sullivan
    1.15
    ulton
    1.14
     Townsend
    1.13
     Rogers
    1.13
     Dunham
    1.12
    Activations Density 0.010%

    No Known Activations