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. 2-RES-JB
    6. 8822
    Prev
    Next
    INDEX
    Explanations

    names of people or places, particularly focusing on the name 'Savannah'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agonist
    -0.83
    ometer
    -0.82
    arent
    -0.79
    itarian
    -0.78
    ometers
    -0.76
    haust
    -0.76
    ļéĨĴ
    -0.72
    ifer
    -0.72
    ative
    -0.71
    bably
    -0.71
    POSITIVE LOGITS
     Savannah
    1.05
     Guth
    0.91
     Montana
    0.81
     Brooke
    0.78
     Shields
    0.75
    annah
    0.75
    sburg
    0.74
     Banks
    0.73
     Loren
    0.73
    ples
    0.72
    Activations Density 0.018%

    No Known Activations