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. 20739
    Prev
    Next
    INDEX
    Explanations

    phrases related to road conditions and equipment used for road maintenance

    oai_token-act-pair · gpt-3.5-turbo

    words related to user submissions or contributions

    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
    worms
    -0.70
    cup
    -0.66
     vomiting
    -0.64
    stead
    -0.63
     hint
    -0.63
     Pyth
    -0.63
    pipe
    -0.62
     dun
    -0.62
    worm
    -0.60
     Roku
    -0.60
    POSITIVE LOGITS
    Reviewer
    1.12
    oÄŁan
    0.82
    edin
    0.75
    idal
    0.75
    oided
    0.73
    orsi
    0.73
    stone
    0.73
    afia
    0.73
    olan
    0.72
     destro
    0.71
    Activations Density 0.000%

    No Known Activations