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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6844
    Prev
    Next
    INDEX
    Explanations

    adjectives that express surprise, interest, or astonishment

    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
    liv
    -0.82
    lam
    -0.62
     frequ
    -0.60
    ãĥı
    -0.58
     rotation
    -0.56
     hell
    -0.55
    ulum
    -0.53
     Init
    -0.52
     boarded
    -0.50
    ogens
    -0.50
    POSITIVE LOGITS
     about
    0.78
    SPONSORED
    0.70
     is
    0.70
     ABOUT
    0.69
    today
    0.69
     here
    0.68
     takeaway
    0.66
    iates
    0.65
    ¶ħ
    0.64
    Ĥª
    0.64
    Activations Density 0.154%

    No Known Activations