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. 11-RES-JB
    6. 8469
    Prev
    Next
    INDEX
    Explanations

    political terms and names

    oai_token-act-pair · gpt-3.5-turbo

    a particular symbol or character across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tid
    -0.71
     Tunis
    -0.67
     Niet
    -0.63
     polyg
    -0.62
     NEC
    -0.61
     Bak
    -0.61
     Borough
    -0.61
     extrap
    -0.61
     pastry
    -0.60
     Mous
    -0.59
    POSITIVE LOGITS
    Ļ
    1.33
    ª
    1.32
    ¡
    1.24
    ı
    1.20
    ħ
    1.20
    ĸ
    1.14
    ¬
    1.13
    Ĵ
    1.11
    Ģ
    1.09
    ¼
    1.09
    Activations Density 0.428%

    No Known Activations