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. 13727
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to sizes, measurements, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly measurements or dimensions

    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
    geist
    -0.85
    achi
    -0.74
    doms
    -0.73
    pocket
    -0.72
    par
    -0.70
    warts
    -0.70
    Fram
    -0.70
     Chronicle
    -0.69
    ports
    -0.67
    actic
    -0.66
    POSITIVE LOGITS
     ILCS
    0.80
    Hz
    0.80
    éĹĺ
    0.79
     sqor
    0.77
     msec
    0.74
    inyl
    0.73
    elsius
    0.72
    PDATE
    0.71
    adeon
    0.69
    fps
    0.69
    Activations Density 0.033%

    No Known Activations