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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17431
    Prev
    Next
    INDEX
    Explanations

    labels and captions for images or posts

    oai_token-act-pair · gpt-3.5-turbo

    sections with document navigational elements and metadata information

    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
     Palest
    -0.75
     Sparrow
    -0.63
    rower
    -0.61
    omore
    -0.59
    gem
    -0.57
    oret
    -0.57
    schild
    -0.56
    stead
    -0.55
     Cyborg
    -0.55
     stre
    -0.55
    POSITIVE LOGITS
     guiActiveUnfocused
    1.04
     Quote
    0.91
     Submit
    0.87
     Thumbnails
    0.87
     »
    0.86
     Download
    0.86
     IMAGES
    0.84
     Loading
    0.84
     Tweet
    0.82
    Hide
    0.82
    Activations Density 0.206%

    No Known Activations