Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20933
    Prev
    Next
    INDEX
    Explanations

    words related to potential technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases implying potential or future developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.81
     Constant
    -0.65
    OLD
    -0.64
     Torn
    -0.63
     Wolves
    -0.60
     Loyal
    -0.59
     Bakr
    -0.59
     Mous
    -0.58
     guessing
    -0.57
     Died
    -0.57
    POSITIVE LOGITS
     outper
    1.11
     someday
    1.11
     enhance
    1.09
     provide
    1.07
     enable
    1.03
     alleviate
    1.02
     replace
    1.02
     integrate
    1.01
     transform
    1.01
     solve
    1.00
    Activations Density 0.324%

    No Known Activations