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. 0-RES-JB
    6. 3620
    Prev
    Next
    INDEX
    Explanations

    words related to the German word "Flüchtlinge", which translates to "refugees" in English

    oai_token-act-pair · gpt-3.5-turbo

    the term "Fl" and variations related to a specific topic or item, likely pertaining to a category or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ay
    -0.80
     recess
    -0.70
     nep
    -0.69
    amera
    -0.68
    ATIVE
    -0.67
    ername
    -0.66
    enge
    -0.65
    Ay
    -0.64
     Ay
    -0.63
     minded
    -0.62
    POSITIVE LOGITS
     Fl
    3.50
    Fl
    2.13
    fl
    1.80
     fl
    1.78
     FL
    1.72
     Flo
    1.45
     Fle
    1.42
    FL
    1.39
     Flare
    1.32
     Flame
    1.30
    Activations Density 0.011%

    No Known Activations