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. 5067
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically related to the name "Matthew"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Matthew."

    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
     satell
    -0.88
    Interstitial
    -0.83
    phy
    -0.83
    PLA
    -0.81
    ãĥ©ãĥ³
    -0.81
    ãĤ´ãĥ³
    -0.81
    ktop
    -0.79
    ntil
    -0.79
    inates
    -0.79
    dylib
    -0.78
    POSITIVE LOGITS
     Stafford
    0.90
     Matthew
    0.88
     Abraham
    0.84
     Shepard
    0.82
     Vaughn
    0.81
     Ridley
    0.81
    hew
    0.80
     Peters
    0.78
     Matthews
    0.74
    hews
    0.74
    Activations Density 0.011%

    No Known Activations