© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12992
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals named Guy

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Guy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.78
    allas
    -0.72
    rums
    -0.72
     denomin
    -0.72
    arching
    -0.72
    recomm
    -0.71
    sequence
    -0.69
    undai
    -0.69
    edded
    -0.69
    etsk
    -0.69
    POSITIVE LOGITS
     Faw
    1.23
     Guy
    0.97
    brush
    0.92
     Cecil
    0.85
     Hug
    0.83
    agne
    0.76
    stown
    0.75
    Guy
    0.74
    WithNo
    0.74
     Trick
    0.74
    Activations Density 0.005%

    No Known Activations