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. 1-RES-JB
    6. 8431
    Prev
    Next
    INDEX
    Explanations

    phrases involving fast and precise movements

    oai_token-act-pair · gpt-3.5-turbo

    words associated with actions involving the manipulation or consumption of food and drink

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENGTH
    -0.67
    ALE
    -0.65
    Reviewer
    -0.64
     Osw
    -0.63
    ORE
    -0.62
     Sax
    -0.61
    Flight
    -0.61
     Orth
    -0.60
    WOOD
    -0.60
    CV
    -0.60
    POSITIVE LOGITS
    bling
    1.41
    bled
    1.31
     drib
    1.20
    bler
    1.16
    bles
    1.13
    bly
    1.05
    blers
    0.97
    ble
    0.94
     dab
    0.89
    ersed
    0.85
    Activations Density 0.011%

    No Known Activations