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. 9-RES-JB
    6. 9537
    Prev
    Next
    INDEX
    Explanations

    comparisons or preferences emphasizing "rather than"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight alternatives or emphasize "rather than."

    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
    meric
    -0.81
    ulner
    -0.73
    cia
    -0.72
    lic
    -0.69
    auer
    -0.66
    STR
    -0.65
    spot
    -0.65
    ESE
    -0.65
    isf
    -0.65
    alde
    -0.64
    POSITIVE LOGITS
     necessarily
    1.25
     relying
    1.10
     merely
    1.08
     simply
    1.01
     bothering
    0.99
     letting
    0.89
     solely
    0.88
     requiring
    0.88
     needing
    0.87
     focusing
    0.87
    Activations Density 0.050%

    No Known Activations