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. 0-RES-JB
    6. 11050
    Prev
    Next
    INDEX
    Explanations

    words and prefixes related to extensions or extensive actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ext" in various contexts

    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
    ña
    -0.78
    izu
    -0.64
    ggy
    -0.64
     faced
    -0.63
     Swan
    -0.63
     Lucky
    -0.62
     wise
    -0.62
     rolls
    -0.62
     bidding
    -0.62
     Photographer
    -0.60
    POSITIVE LOGITS
    ext
    4.08
    Ext
    2.09
     Ext
    1.60
    EXT
    1.47
     ext
    1.42
     Extension
    1.32
     extension
    1.28
    expl
    1.27
     EXT
    1.24
    ex
    1.21
    Activations Density 0.005%

    No Known Activations