Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6302
    Prev
    Next
    INDEX
    Explanations

    mentions of animal-related entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to animals and animal-related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chool
    -0.87
    creen
    -0.85
     Compton
    -0.82
    hips
    -0.81
    paces
    -0.76
    pring
    -0.75
    gaard
    -0.72
    ession
    -0.71
    lain
    -0.71
    jong
    -0.71
    POSITIVE LOGITS
     carc
    0.90
     welfare
    0.85
    aclysm
    0.83
     kingdom
    0.83
    Animal
    0.82
     cruelty
    0.81
     mammal
    0.79
     animal
    0.79
    alogue
    0.79
     species
    0.79
    Activations Density 0.029%

    No Known Activations