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. 8-RES-JB
    6. 16203
    Prev
    Next
    INDEX
    Explanations

    visual representations such as images, diagrams, charts, and graphs

    oai_token-act-pair · gpt-3.5-turbo

    visual representations, such as images, charts, and diagrams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iability
    -0.71
    ebus
    -0.71
    BuyableInstoreAndOnline
    -0.70
    cellence
    -0.68
    aples
    -0.68
    noxious
    -0.66
    forces
    -0.66
    icc
    -0.65
     revoked
    -0.65
    ailability
    -0.64
    POSITIVE LOGITS
     below
    1.22
     screenshot
    1.17
     illustrating
    1.13
     illustration
    1.12
     depicts
    1.12
    below
    1.09
     Thumbnails
    1.07
     gallery
    1.06
     illustrates
    1.04
     above
    1.00
    Activations Density 0.171%

    No Known Activations