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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 8974
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Laura"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.79
    rated
    -0.72
    nings
    -0.68
    */(
    -0.66
    fleet
    -0.66
    rue
    -0.65
    hire
    -0.65
    mental
    -0.64
    MENTS
    -0.63
    cffffcc
    -0.63
    POSITIVE LOGITS
     Jane
    1.08
     Palmer
    1.04
     Bates
    0.90
     Bloom
    0.89
     Ing
    0.87
    Jane
    0.84
    anne
    0.82
     Vo
    0.81
     Bush
    0.80
     Anne
    0.79
    Activations Density 0.031%

    No Known Activations