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. 3428
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific individuals, particularly those named Nadine and Nate

    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
     Burnett
    -0.85
     Burns
    -0.75
     Giles
    -0.72
    agger
    -0.71
     Rapids
    -0.71
    ston
    -0.70
     Flower
    -0.70
     Champ
    -0.69
     Cast
    -0.68
     Stall
    -0.68
    POSITIVE LOGITS
     Nad
    1.92
     Nu
    1.69
     Ni
    1.68
    N
    1.54
    NM
    1.53
    NH
    1.49
     Nun
    1.47
     NM
    1.47
     ND
    1.47
     N
    1.46
    Activations Density 0.066%

    No Known Activations