© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18296
    Prev
    Next
    INDEX
    Explanations

    hobby-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to hobbies

    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
     Syri
    -0.70
     IMF
    -0.68
     Govern
    -0.66
     Covenant
    -0.65
     Laf
    -0.65
    equality
    -0.64
    illes
    -0.64
     Def
    -0.63
     Aval
    -0.63
     Exec
    -0.61
    POSITIVE LOGITS
     hobby
    4.02
     hobbies
    2.13
     Hobby
    2.10
     enthusiast
    1.38
     homebrew
    1.35
     enthusiasts
    1.25
     fandom
    1.17
     profession
    1.12
     amateur
    1.12
     geek
    1.10
    Activations Density 0.022%

    No Known Activations