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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 277
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Matt"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mat" or variations thereof in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.88
    ngth
    -0.79
    OHN
    -0.77
    ¥ŀ
    -0.74
    æĸ¹
    -0.73
    hower
    -0.73
    ãĤī
    -0.72
     downhill
    -0.70
     confir
    -0.70
    ITED
    -0.69
    POSITIVE LOGITS
    hematic
    1.39
    hematically
    1.28
    ilda
    1.25
    hews
    1.21
    urity
    1.21
    hew
    1.14
    hemat
    1.12
    ches
    1.10
    rices
    1.08
    ting
    1.06
    Activations Density 0.011%

    No Known Activations