Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 5362
    Prev
    Next
    INDEX
    Explanations

    names of individuals or places within a legal or investigative context

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to individuals and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughtered
    -0.63
    berra
    -0.62
     humans
    -0.56
    į
    -0.56
    higher
    -0.55
    ¥ŀ
    -0.55
     Scientists
    -0.55
    modules
    -0.55
    Big
    -0.54
    Meat
    -0.54
    POSITIVE LOGITS
    's
    0.97
     himself
    0.95
     herself
    0.88
    hyde
    0.79
     Industries
    0.77
    tsy
    0.76
     Jr
    0.74
     Sr
    0.74
     accuser
    0.72
     vetoed
    0.72
    Activations Density 0.216%

    No Known Activations