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. 7-RES-JB
    6. 9130
    Prev
    Next
    INDEX
    Explanations

    locations or places denoted by the term "headquarters"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating organizational or institutional affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pieces
    -0.90
     roar
    -0.84
     gaps
    -0.74
     chops
    -0.74
    bows
    -0.74
    beam
    -0.69
     flakes
    -0.69
    berries
    -0.68
     ears
    -0.68
    boats
    -0.66
    POSITIVE LOGITS
    interstitial
    0.83
     congress
    0.80
     Directorate
    0.79
     Representative
    0.78
     Government
    0.78
    IDA
    0.78
     State
    0.77
     Senator
    0.77
     Ministry
    0.76
     Tourism
    0.76
    Activations Density 0.197%

    No Known Activations