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. 20384
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical appearance, specifically focusing on hair color and style

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to physical appearance, particularly focusing on hair color and other notable characteristics

    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
    ettings
    -1.00
    Ô
    -0.97
     Cosponsors
    -0.88
    inventoryQuantity
    -0.84
    âķIJ
    -0.84
    ciplinary
    -0.80
    odium
    -0.76
    ctica
    -0.75
    rences
    -0.74
    atories
    -0.74
    POSITIVE LOGITS
     bearded
    0.93
     wig
    0.93
    haired
    0.92
     gorilla
    0.89
     blond
    0.88
     ape
    0.87
     warrior
    0.86
     waiter
    0.85
     dragon
    0.84
     blonde
    0.84
    Activations Density 0.094%

    No Known Activations