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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4624
    Prev
    Next
    INDEX
    Explanations

    words related to geology and rock formation processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veterinary
    -0.69
    hack
    -0.69
     courier
    -0.67
     Charisma
    -0.67
    Joy
    -0.66
     TTL
    -0.66
     Yamaha
    -0.66
     typew
    -0.65
     Nursing
    -0.65
    ////////
    -0.65
    POSITIVE LOGITS
     bedrock
    1.46
     sediment
    1.38
     mantle
    1.37
     crust
    1.29
     limestone
    1.29
     deposits
    1.26
     shale
    1.21
     layers
    1.21
     minerals
    1.20
     volcanic
    1.19
    Activations Density 0.434%

    No Known Activations