© 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. 11-RES-JB
    11. 24433
    Prev
    Next
    INDEX
    Explanations

    references to sports scores and leads

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical advantages or scoring in competitive contexts

    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
    arus
    -0.69
    romy
    -0.67
     acron
    -0.63
     concess
    -0.61
     menus
    -0.60
    aida
    -0.59
    mbuds
    -0.58
    ammad
    -0.58
    ibur
    -0.57
     unemploy
    -0.57
    POSITIVE LOGITS
    breaker
    0.89
     heading
    0.84
     over
    0.80
    OVER
    0.78
    over
    0.76
    break
    0.76
    breaking
    0.75
    stre
    0.73
    holding
    0.72
    noon
    0.71
    Activations Density 0.080%

    No Known Activations