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. 3838
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication

    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
    ãĤ·ãĥ£
    -0.85
    ãĥ¯
    -0.79
    DragonMagazine
    -0.74
    æµ
    -0.73
    razil
    -0.71
    dylib
    -0.70
    gart
    -0.70
    ãĥª
    -0.69
    ãĤµ
    -0.67
    ffee
    -0.67
    POSITIVE LOGITS
     against
    1.23
     loudly
    1.14
     furiously
    1.12
     extensively
    1.10
     peacefully
    1.08
     tirelessly
    1.03
     vigorously
    0.97
     aggressively
    0.96
     confidently
    0.96
     anonymously
    0.93
    Activations Density 0.186%

    No Known Activations