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. 5734
    Prev
    Next
    INDEX
    Explanations

    references to animals

    oai_token-act-pair · gpt-3.5-turbo

    references to animals

    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
    tesy
    -0.83
     Revis
    -0.71
     Rosenberg
    -0.71
     Boom
    -0.71
     diplom
    -0.70
     Strongh
    -0.69
     Rankings
    -0.69
     Reborn
    -0.66
    æŃ¦
    -0.66
    nels
    -0.64
    POSITIVE LOGITS
     animal
    3.64
    animal
    2.90
    Animal
    2.76
     animals
    2.64
     Animal
    2.54
     Animals
    2.25
     mammal
    2.06
     rodent
    1.94
     canine
    1.74
    Anim
    1.66
    Activations Density 0.015%

    No Known Activations