© 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. 11-RES-JB
    11. 21348
    Prev
    Next
    INDEX
    Explanations

    text related to soccer/football, focusing on players, managers, and team actions

    oai_token-act-pair · gpt-3.5-turbo

    references to football club management and player transfers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollah
    -1.03
     Anchorage
    -1.01
    natureconservancy
    -0.92
    oka
    -0.86
    cycles
    -0.85
     bicycl
    -0.81
     Alaska
    -0.81
     Palin
    -0.80
     aval
    -0.78
     Glacier
    -0.78
    POSITIVE LOGITS
     Mourinho
    2.06
     Chelsea
    1.76
     Manchester
    1.64
    Chelsea
    1.61
    Manchester
    1.59
     Trafford
    1.53
     Everton
    1.51
     Stamford
    1.50
     Rooney
    1.44
     Guardiola
    1.38
    Activations Density 0.201%

    No Known Activations