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. 10-RES-JB
    6. 9603
    Prev
    Next
    INDEX
    Explanations

    spelling variants of common words

    oai_token-act-pair · gpt-3.5-turbo

    signs of high numerical values or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.74
    umblr
    -0.63
    ittal
    -0.62
    oat
    -0.62
    ahan
    -0.62
    entimes
    -0.62
    ively
    -0.61
    agues
    -0.61
    etsk
    -0.61
    ghai
    -0.60
    POSITIVE LOGITS
     EDITION
    1.51
    THE
    1.44
     STORY
    1.41
    SPEC
    1.36
     DAY
    1.36
    LET
    1.35
     ORDER
    1.34
     THE
    1.34
    DAY
    1.33
     VOL
    1.33
    Activations Density 0.144%

    No Known Activations