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. 2395
    Prev
    Next
    INDEX
    Explanations

    the name "Matt"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Matt."

    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
    FUL
    -0.91
    CHO
    -0.80
    GROUND
    -0.75
    dylib
    -0.74
    DragonMagazine
    -0.74
     toile
    -0.73
    gary
    -0.73
    ģĸ
    -0.69
     sophistic
    -0.68
    VALUE
    -0.68
    POSITIVE LOGITS
    achine
    1.11
    hew
    1.03
    apan
    0.99
    ias
    0.98
    uring
    0.97
    ocks
    0.97
    hews
    0.96
     Murd
    0.94
     Damon
    0.94
    eson
    0.90
    Activations Density 0.013%

    No Known Activations