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. 1-RES-JB
    6. 23771
    Prev
    Next
    INDEX
    Explanations

    mentions of Malaysia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to Malaysia

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arettes
    -0.75
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.67
     Patron
    -0.66
     calculated
    -0.66
     FACE
    -0.65
    CHA
    -0.65
    BOOK
    -0.65
     VIDE
    -0.63
     NETWORK
    -0.60
     RIS
    -0.59
    POSITIVE LOGITS
    colm
    1.30
     Lumpur
    1.12
    icious
    1.00
    querade
    0.96
    acca
    0.91
    Mal
    0.91
    mal
    0.90
    vertising
    0.87
    acia
    0.87
    onso
    0.82
    Activations Density 0.003%

    No Known Activations