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. 21107
    Prev
    Next
    INDEX
    Explanations

    adjectives related to small size

    oai_token-act-pair · gpt-3.5-turbo

    references to "little" items or beings, often emphasizing their significance or characteristics

    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
    chwitz
    -0.81
    igham
    -0.77
    worthiness
    -0.76
    idents
    -0.75
    ï¸
    -0.75
    iris
    -0.71
    iership
    -0.70
    restling
    -0.69
    ident
    -0.68
    ocobo
    -0.68
    POSITIVE LOGITS
     bit
    1.04
     girl
    0.91
     boy
    0.88
     brother
    0.84
     snippets
    0.83
     kid
    0.83
     sister
    0.82
     girls
    0.80
     boys
    0.80
     helper
    0.79
    Activations Density 0.028%

    No Known Activations