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. 4988
    Prev
    Next
    INDEX
    Explanations

    European languages and phrases with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly those commonly used in various languages or scripts

    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
     traff
    -0.67
     Wanted
    -0.67
     Traff
    -0.64
    itious
    -0.64
    alez
    -0.63
    ifier
    -0.63
    packing
    -0.63
     applic
    -0.62
     drawer
    -0.61
    dfx
    -0.60
    POSITIVE LOGITS
    Ãł
    1.09
    ¬
    1.03
    issance
    0.94
    ¹
    0.92
    ¸
    0.91
    ´
    0.90
    ñ
    0.89
    ï
    0.89
    Å¡
    0.85
     la
    0.85
    Activations Density 0.003%

    No Known Activations