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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 16250
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, especially those containing the substring "leigh"

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with individuals and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drag
    -0.74
     Stard
    -0.71
    hest
    -0.70
     Illum
    -0.69
     Galactic
    -0.69
     Torch
    -0.67
    teenth
    -0.66
    gression
    -0.65
     Anim
    -0.65
    Drag
    -0.64
    POSITIVE LOGITS
    leigh
    1.57
     gateway
    1.29
    adding
    1.25
    ammers
    1.25
     Leigh
    1.21
    ennett
    1.10
    odge
    1.08
    omers
    1.04
     surround
    1.00
    omas
    0.97
    Activations Density 0.066%

    No Known Activations