Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19314
    Prev
    Next
    INDEX
    Explanations

    references to the Arsenal football manager Arsène Wenger

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Wenger."

    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
    âĶĢâĶĢâĶĢâĶĢ
    -0.75
    PsyNetMessage
    -0.67
    obo
    -0.63
    ateral
    -0.63
    oration
    -0.62
    croft
    -0.61
    cess
    -0.60
    mits
    -0.60
    ceed
    -0.59
    ocard
    -0.59
    POSITIVE LOGITS
     Wenger
    1.20
    pin
    0.81
    sonian
    0.75
    wich
    0.71
    theless
    0.69
    nesday
    0.69
     Bros
    0.69
    worms
    0.68
    icz
    0.68
    ukong
    0.67
    Activations Density 0.003%

    No Known Activations