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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 83
    Prev
    Next
    INDEX
    Explanations

    Italian words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'il'

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

    the Italian definite article 'il'

    oai_token-act-pair · gpt-4-turbo
    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
    taining
    -0.89
    lished
    -0.80
    geon
    -0.71
    cycles
    -0.70
    restrial
    -0.69
    bucks
    -0.67
    modules
    -0.67
    chrome
    -0.66
    contract
    -0.65
    âĶģ
    -0.63
    POSITIVE LOGITS
    vl
    1.11
     il
    0.90
     mog
    0.85
     tem
    0.82
    uminati
    0.81
    inois
    0.76
    ength
    0.76
    ibrary
    0.75
    umin
    0.74
    estial
    0.71
    Activations Density 0.006%

    No Known Activations