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. 17573
    Prev
    Next
    INDEX
    Explanations

    document authors or content creators

    oai_token-act-pair · gpt-3.5-turbo

    words associated with authorship or recognition of written works

    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
     dismiss
    -0.69
     retweet
    -0.64
     Safari
    -0.64
     lob
    -0.64
     now
    -0.63
     moons
    -0.63
     pinpoint
    -0.63
     champion
    -0.62
     stout
    -0.62
     cent
    -0.61
    POSITIVE LOGITS
     Written
    4.30
    Written
    1.67
     Helpful
    1.53
     ********************************
    1.31
     =================================================================
    1.20
     Recorded
    1.17
     Published
    1.17
     Become
    1.08
     Contents
    1.05
    iless
    1.04
    Activations Density 0.036%

    No Known Activations