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. 10819
    Prev
    Next
    INDEX
    Explanations

    statements starting with "As" and followed by a profession or personal background descriptor

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal perspectives or experiences

    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
     Emin
    -0.75
    arat
    -0.74
    Reloaded
    -0.72
    OTO
    -0.67
    »Ĵ
    -0.67
     Replacement
    -0.63
     reversible
    -0.63
     Plague
    -0.62
    quished
    -0.60
     Continuing
    -0.60
    POSITIVE LOGITS
     acutely
    0.93
     instinctively
    0.90
     intimately
    0.89
     naturally
    0.84
     privileged
    0.82
     empath
    0.82
     firsthand
    0.81
     constantly
    0.79
     deeply
    0.79
    idents
    0.78
    Activations Density 0.336%

    No Known Activations