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. 0-RES-JB
    6. 4468
    Prev
    Next
    INDEX
    Explanations

    the word "Even" followed by a spacing number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "even"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caps
    -0.69
     linkage
    -0.66
     type
    -0.63
     part
    -0.62
     sec
    -0.60
     below
    -0.60
    lled
    -0.60
     named
    -0.59
     deceased
    -0.59
    que
    -0.58
    POSITIVE LOGITS
     Even
    2.65
    Even
    2.08
    even
    1.83
     EVEN
    1.82
     Especially
    1.71
     Despite
    1.61
     Worse
    1.60
     Moreover
    1.59
     Although
    1.55
     Though
    1.55
    Activations Density 0.017%

    No Known Activations