© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71
    Prev
    Next
    INDEX
    Explanations

    mentions of hobbies

    oai_token-act-pair · gpt-3.5-turbo

    references to hobbies and related activities

    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
     skulls
    -0.65
    acements
    -0.64
     Apostles
    -0.64
    oti
    -0.63
     Ezekiel
    -0.63
    arers
    -0.62
     Romans
    -0.60
    ×Ļ×
    -0.60
    osion
    -0.60
     Africans
    -0.60
    POSITIVE LOGITS
     hobby
    1.20
    sonian
    0.89
    icion
    0.87
    reprene
    0.86
    Shop
    0.85
    istry
    0.84
    ist
    0.84
    finder
    0.83
    bench
    0.82
     fixme
    0.79
    Activations Density 0.018%

    No Known Activations