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. 8-RES-JB
    6. 9098
    Prev
    Next
    INDEX
    Explanations

    the letter "Y" followed by various combinations of other letters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'Y' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wonderland
    -0.72
     Prelude
    -0.69
     Cortana
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.66
     Excellence
    -0.63
    versions
    -0.63
     "$:/
    -0.61
    neapolis
    -0.61
     Creed
    -0.60
     Staples
    -0.59
    POSITIVE LOGITS
    ield
    1.11
    onder
    1.07
    von
    1.02
    ank
    0.99
    acht
    0.98
    aku
    0.97
    ahoo
    0.93
    anks
    0.93
    LD
    0.93
    ummy
    0.93
    Activations Density 0.026%

    No Known Activations