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. 24423
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Wayne

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Wayne."

    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
    rador
    -1.12
    yrinth
    -1.03
    gently
    -0.91
    gerald
    -0.81
    avorite
    -0.75
    iar
    -0.75
    TAIN
    -0.70
    alion
    -0.69
    */(
    -0.68
    inally
    -0.67
    POSITIVE LOGITS
     Gret
    0.96
     Enterprises
    0.92
     Rooney
    0.91
     Manor
    0.83
    pton
    0.80
     Beach
    0.75
     Wayne
    0.75
     Til
    0.75
    ufact
    0.74
     Dug
    0.73
    Activations Density 0.012%

    No Known Activations