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. 16022
    Prev
    Next
    INDEX
    Explanations

    Italian names ending in '-li' and various other Italian-related words

    oai_token-act-pair · gpt-3.5-turbo

    forms of the syllable 'li' or 'u'

    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
    ãĤ´ãĥ³
    -0.64
     circles
    -0.63
     coli
    -0.62
     differential
    -0.60
     furthe
    -0.57
    plain
    -0.56
     stal
    -0.55
    pole
    -0.55
     Suz
    -0.55
     same
    -0.54
    POSITIVE LOGITS
    andise
    0.97
    ultural
    0.84
    iani
    0.83
    omo
    0.82
    iano
    0.79
    ldom
    0.79
    actory
    0.79
    ierrez
    0.78
    ulture
    0.77
    iru
    0.76
    Activations Density 0.207%

    No Known Activations