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. 3133
    Prev
    Next
    INDEX
    Explanations

    animals

    oai_token-act-pair · gpt-3.5-turbo

    references to animals and their characteristics or actions

    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
     oversight
    -0.87
     appropriations
    -0.85
     Oversight
    -0.75
     affirmative
    -0.75
    quickShipAvailable
    -0.71
     Disclosure
    -0.71
     entitle
    -0.68
    icit
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
     implementation
    -0.67
    POSITIVE LOGITS
    ensis
    0.96
     nests
    0.88
    vae
    0.85
    birds
    0.80
     fungus
    0.80
     reptiles
    0.79
    auri
    0.78
     worms
    0.77
     nib
    0.77
     larvae
    0.76
    Activations Density 0.946%

    No Known Activations