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. 1256
    Prev
    Next
    INDEX
    Explanations

    mentions of animals or references related to animals

    oai_token-act-pair · gpt-3.5-turbo

    references to animals and animal welfare topics

    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
    jong
    -0.74
    orship
    -0.66
     Compton
    -0.66
    unda
    -0.65
    nance
    -0.64
    inen
    -0.64
     sugg
    -0.63
    lining
    -0.63
    heit
    -0.62
    pai
    -0.61
    POSITIVE LOGITS
     animal
    1.20
     animals
    1.06
    animal
    1.02
     carc
    1.02
     mammals
    1.01
     mammal
    1.01
    Animal
    0.97
     Animal
    0.89
     species
    0.86
    Anim
    0.85
    Activations Density 0.012%

    No Known Activations