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. 4-RES-JB
    6. 4962
    Prev
    Next
    INDEX
    Explanations

    ingredients used in breakfast dishes

    oai_token-act-pair · gpt-3.5-turbo

    references to bacon in various contexts

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

    No Comments

    Negative Logits
    ept
    -0.82
     Fundamental
    -0.80
     Volunte
    -0.73
     Scientology
    -0.72
    oric
    -0.70
     Cheong
    -0.70
    inen
    -0.68
    å§«
    -0.65
    hips
    -0.65
     Occupations
    -0.65
    POSITIVE LOGITS
    halla
    1.13
    nect
    1.05
     grease
    1.05
    netflix
    1.05
     bacon
    1.04
     chees
    0.93
    fruit
    0.91
     toast
    0.90
    wallet
    0.82
     Bacon
    0.78
    Activations Density 0.011%

    No Known Activations