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. 10-RES-JB
    6. 22014
    Prev
    Next
    INDEX
    Explanations

    numbers related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    percentage values expressed in a concise format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ready
    -0.66
    é¾įå¥ij士
    -0.64
    ryu
    -0.64
    ModLoader
    -0.63
    BO
    -0.62
    Rocket
    -0.60
     Storage
    -0.60
    RAW
    -0.60
    ä
    -0.60
    BuyableInstoreAndOnline
    -0.58
    POSITIVE LOGITS
     cent
    1.33
    icent
    0.89
    cent
    0.81
     cm
    0.79
    %).
    0.77
    %)
    0.77
     lakh
    0.76
    cm
    0.76
    malink
    0.75
    cill
    0.74
    Activations Density 0.015%

    No Known Activations