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. 20803
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "earlier" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "earlier."

    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
    idth
    -0.61
    oster
    -0.59
    ctors
    -0.56
    yr
    -0.54
    ots
    -0.54
    tin
    -0.54
    ↵Âł
    -0.53
     mathemat
    -0.53
    ensity
    -0.52
     testament
    -0.52
    POSITIVE LOGITS
     earlier
    3.44
     previous
    1.79
     later
    1.78
     Earlier
    1.73
     previously
    1.66
     prior
    1.56
     early
    1.52
     sooner
    1.52
     yesterday
    1.51
    Earlier
    1.50
    Activations Density 0.017%

    No Known Activations