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. 9-RES-JB
    6. 14449
    Prev
    Next
    INDEX
    Explanations

    quoted text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks indicating spoken dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     sacked
    -0.74
     favour
    -0.72
     arch
    -0.71
     signalling
    -0.67
     listed
    -0.66
     smoot
    -0.66
     moder
    -0.62
     surname
    -0.62
     finished
    -0.62
     graz
    -0.62
    POSITIVE LOGITS
    We
    1.45
    Our
    1.39
    Everybody
    1.36
    It
    1.33
    Nobody
    1.33
    Obviously
    1.32
    They
    1.32
    Absolutely
    1.31
    I
    1.30
    There
    1.29
    Activations Density 0.131%

    No Known Activations