© 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. 7-RES-JB
    11. 12369
    Prev
    Next
    INDEX
    Explanations

    mentions of the sport rugby

    oai_token-act-pair · gpt-3.5-turbo

    references to rugby and rugby league

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.96
     Hoover
    -0.86
    iment
    -0.84
    iments
    -0.80
    places
    -0.76
    ression
    -0.75
    eanor
    -0.75
    ortion
    -0.74
    roxy
    -0.72
    igible
    -0.71
    POSITIVE LOGITS
     league
    0.89
     union
    0.86
     rugby
    0.78
     feder
    0.71
     referees
    0.71
     scr
    0.70
     Premiership
    0.68
    atu
    0.68
     Rugby
    0.67
     federation
    0.67
    Activations Density 0.026%

    No Known Activations