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. 9-RES-JB
    6. 8144
    Prev
    Next
    INDEX
    Explanations

    mentions of animals, specifically sheep and cattle

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvant
    -0.79
    AMI
    -0.78
     fortun
    -0.75
     validity
    -0.73
    âĶģ
    -0.71
    SPONSORED
    -0.71
    ioxide
    -0.70
    uyomi
    -0.68
     unlaw
    -0.68
    ENTS
    -0.67
    POSITIVE LOGITS
    skin
    1.14
     grazing
    1.01
     gra
    1.00
    dogs
    0.96
    ishly
    0.92
     ranc
    0.91
     pasture
    0.87
     carc
    0.87
    stra
    0.86
    yard
    0.85
    Activations Density 0.062%

    No Known Activations