© 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
    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. 8042
    Prev
    Next
    INDEX
    Explanations

    references to football or soccer and terms related to poverty

    oai_token-act-pair · gpt-3.5-turbo

    references to football and associated themes

    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
     Royale
    -0.72
     constitu
    -0.70
     Sens
    -0.67
     LIA
    -0.67
     Superior
    -0.63
     colleg
    -0.62
    ansson
    -0.62
    naire
    -0.62
    £ı
    -0.61
     Bund
    -0.60
    POSITIVE LOGITS
    Football
    2.47
    overty
    1.75
    football
    1.47
    BALL
    1.22
    Child
    1.18
     cheat
    1.17
    Kick
    0.87
    tml
    0.86
    Break
    0.86
    ãĥĬ
    0.86
    Activations Density 0.027%

    No Known Activations