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. 3-RES-JB
    6. 11791
    Prev
    Next
    INDEX
    Explanations

    words related to physical features, particularly eye color and hair color

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to physical appearance, specifically eye and hair color

    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
    è£ħ
    -0.72
    isite
    -0.71
    nesota
    -0.71
    Services
    -0.71
    ENT
    -0.68
    cial
    -0.67
    ��
    -0.66
     Layer
    -0.65
    INTER
    -0.65
    scribed
    -0.64
    POSITIVE LOGITS
    eyed
    0.96
     eyed
    0.94
    ness
    0.93
    hog
    0.90
    haired
    0.87
    gling
    0.86
     eyeb
    0.83
     peas
    0.82
    own
    0.80
    nesses
    0.71
    Activations Density 0.030%

    No Known Activations