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. 7-RES-JB
    6. 15889
    Prev
    Next
    INDEX
    Explanations

    names containing the specific string "ik" followed by a single digit or in some cases a word

    oai_token-act-pair · gpt-3.5-turbo

    words that include the substring "ik"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poppy
    -0.69
     Winchester
    -0.64
     DMV
    -0.63
     Malf
    -0.62
    FFFF
    -0.58
     goose
    -0.58
    DIT
    -0.58
    mpeg
    -0.57
     fide
    -0.56
     Merry
    -0.55
    POSITIVE LOGITS
    achu
    1.25
    ernel
    1.16
    ernels
    1.13
    rish
    1.06
    hs
    1.06
    yu
    1.03
    ileaks
    1.01
    ku
    1.01
    owski
    0.97
    istan
    0.97
    Activations Density 0.033%

    No Known Activations