© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 5808
    Prev
    Next
    INDEX
    Explanations

    the name "Van Gaal" specifically

    oai_token-act-pair · gpt-3.5-turbo

    mentions of football managers, particularly Louis van Gaal and Pep Guardiola

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nep
    -0.69
    itions
    -0.67
    ym
    -0.64
    ENCY
    -0.63
    othy
    -0.62
     mammals
    -0.61
    obo
    -0.60
    abet
    -0.59
    ulf
    -0.59
    amaz
    -0.58
    POSITIVE LOGITS
     Gaal
    0.95
     Guardiola
    0.82
     coached
    0.73
    ovic
    0.73
     Wenger
    0.71
     preached
    0.71
    wich
    0.69
     Canaver
    0.68
    agher
    0.68
    edin
    0.68
    Activations Density 0.016%

    No Known Activations