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. 3825
    Prev
    Next
    INDEX
    Explanations

    statements related to actions performed by individuals or groups

    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
    assi
    -0.78
    orum
    -0.60
     risen
    -0.57
     Breaker
    -0.57
    usha
    -0.56
     Shining
    -0.55
    ses
    -0.55
     Flavoring
    -0.54
     usefulness
    -0.54
     runway
    -0.54
    POSITIVE LOGITS
     concurrently
    1.14
     electronically
    1.06
     privately
    1.05
     indoors
    1.01
     anonymously
    1.00
     collabor
    0.98
     differently
    0.96
     exclusively
    0.95
     cheaply
    0.94
     outdoors
    0.93
    Activations Density 0.344%

    No Known Activations