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. 3-RES-JB
    6. 14868
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names 'Alfred' and 'Gustav'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific historical figures, particularly those named Alfred and Gustav

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cript
    -0.88
    BOOK
    -0.82
    stakes
    -0.82
    former
    -0.74
    leading
    -0.73
    hazard
    -0.71
    leaders
    -0.71
    boarding
    -0.70
    PLAY
    -0.70
    ItemImage
    -0.70
    POSITIVE LOGITS
    sson
    1.17
    sburg
    0.90
    ulla
    0.81
     Alfred
    0.78
     Penny
    0.77
    ibrary
    0.75
    rey
    0.75
     obser
    0.74
    ury
    0.72
    rade
    0.72
    Activations Density 0.008%

    No Known Activations