© 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. 2803
    Prev
    Next
    INDEX
    Explanations

    names or references to the same person, likely a famous individual

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of specific names

    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
     Planned
    -0.70
     pat
    -0.68
     Alpha
    -0.62
     schools
    -0.61
     Haram
    -0.61
     mental
    -0.60
     Debbie
    -0.60
     houses
    -0.59
     operations
    -0.59
     trash
    -0.59
    POSITIVE LOGITS
    sson
    5.22
    ansson
    1.52
    kson
    1.42
    son
    1.37
    qv
    1.28
    lund
    1.20
    ð
    1.20
    oglu
    1.20
    riks
    1.14
    onen
    1.13
    Activations Density 0.019%

    No Known Activations