© 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. 4-RES-JB
    11. 10197
    Prev
    Next
    INDEX
    Explanations

    references to winning medals in sports competitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to winning medals, specifically bronze medals in sports events

    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
    ibrary
    -0.84
    adata
    -0.76
     memos
    -0.73
    monitor
    -0.73
    research
    -0.69
    umblr
    -0.68
    properties
    -0.68
    existing
    -0.68
    seless
    -0.65
    Requires
    -0.65
    POSITIVE LOGITS
     finals
    1.28
     championship
    1.24
     Championship
    1.15
     rematch
    1.10
     undefeated
    1.09
     championships
    1.09
    ampions
    1.08
     Championships
    1.08
     standings
    1.07
     tournament
    1.06
    Activations Density 0.896%

    No Known Activations