© 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. 9-RES-JB
    11. 7379
    Prev
    Next
    INDEX
    Explanations

    references to sport events and locations

    oai_token-act-pair · gpt-3.5-turbo

    events involving sports crowds and athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emphas
    -0.86
     recognise
    -0.85
    CHQ
    -0.84
     scept
    -0.83
    Labour
    -0.83
     maths
    -0.82
     realise
    -0.81
    alys
    -0.81
     learnt
    -0.80
     realised
    -0.80
    POSITIVE LOGITS
     ESPN
    1.56
     NFL
    1.42
     jerseys
    1.41
     NBA
    1.39
     Sports
    1.34
     locker
    1.33
     NASCAR
    1.31
     MLB
    1.29
     Stadium
    1.28
    Sports
    1.28
    Activations Density 1.480%

    No Known Activations