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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14147
    Prev
    Next
    INDEX
    Explanations

    words related to programming, technology, and specific terms used in coding such as 'variable', 'method', 'infringement', 'disturbance', and 'class'

    oai_token-act-pair · gpt-3.5-turbo

    elements related to structure and organization within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.83
    avorite
    -0.72
    bledon
    -0.71
    enegger
    -0.70
    bley
    -0.69
     helicop
    -0.69
     Vaugh
    -0.67
    oppable
    -0.67
     Niet
    -0.64
    aeda
    -0.62
    POSITIVE LOGITS
     largeDownload
    0.55
     GR
    0.55
     AMD
    0.50
    gr
    0.50
     Squirrel
    0.50
    alyses
    0.49
     User
    0.49
     Maul
    0.48
    odes
    0.48
     ROCK
    0.47
    Activations Density 0.605%

    No Known Activations