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. 345
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "till" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to time or deadlines

    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
     specifically
    -0.63
    NAME
    -0.59
     Huff
    -0.59
     STAT
    -0.58
    isco
    -0.57
     potentially
    -0.56
    BILITIES
    -0.56
    eredith
    -0.56
    asc
    -0.55
     extrad
    -0.55
    POSITIVE LOGITS
     till
    3.64
     til
    1.88
     Till
    1.60
     until
    1.46
    until
    1.46
    til
    1.35
     Til
    1.10
     tho
    1.05
    Until
    1.00
     onwards
    1.00
    Activations Density 0.016%

    No Known Activations