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. 9-RES-JB
    6. 401
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or regulatory actions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate compliance or adherence to regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.84
     dimensional
    -0.79
     bullish
    -0.78
     fascination
    -0.73
     electr
    -0.72
     inspir
    -0.71
    marine
    -0.70
     satell
    -0.70
     strap
    -0.70
     regener
    -0.69
    POSITIVE LOGITS
     Previously
    1.27
     However
    1.23
     Otherwise
    1.23
     Meaning
    1.22
     Individuals
    1.22
     Critics
    1.20
     Applic
    1.18
     Therefore
    1.16
     Typically
    1.16
     Additionally
    1.15
    Activations Density 0.474%

    No Known Activations