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. 8-RES-JB
    6. 15447
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Morris" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Morris."

    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
    mate
    -0.72
    choes
    -0.71
    REAM
    -0.68
    sheet
    -0.67
    fare
    -0.67
    pta
    -0.65
    ccording
    -0.64
    Hispanic
    -0.64
    rium
    -0.64
    tics
    -0.62
    POSITIVE LOGITS
    sey
    1.74
    olini
    0.92
    ison
    0.90
    seys
    0.89
     Morris
    0.83
    rison
    0.82
    dale
    0.82
    usalem
    0.80
    ussen
    0.80
    pora
    0.79
    Activations Density 0.035%

    No Known Activations