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. 11631
    Prev
    Next
    INDEX
    Explanations

    mentions of countries and political figures

    oai_token-act-pair · gpt-3.5-turbo

    specific letter combinations, particularly those resembling the character "â" and its variants

    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
     accessory
    -0.71
    ifications
    -0.66
    aimon
    -0.66
     giveaway
    -0.66
     NEC
    -0.65
     implant
    -0.65
     ellipt
    -0.65
    isode
    -0.63
     commissions
    -0.63
     scatter
    -0.63
    POSITIVE LOGITS
    ¬
    1.36
    £
    1.15
    ħ
    1.13
    Ń
    1.12
    ²
    1.10
    ı
    1.10
    Ĵ
    1.10
    ª
    1.08
    º
    1.05
    ¹
    1.05
    Activations Density 0.165%

    No Known Activations