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. 3-RES-JB
    6. 8019
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numbers and entities, particularly in contexts related to gaming or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.70
     guiActiveUnfocused
    -0.65
    EStreamFrame
    -0.64
    rawdownloadcloneembedreportprint
    -0.62
    tumblr
    -0.61
    EStream
    -0.57
    isSpecialOrderable
    -0.57
    ryu
    -0.57
    bleacher
    -0.56
    ãĤ´ãĥ³
    -0.56
    POSITIVE LOGITS
     Citiz
    0.60
    ĩ
    0.60
    ·
    0.57
    °
    0.55
     metic
    0.53
     unpop
    0.53
     neigh
    0.52
     unden
    0.52
    ikan
    0.51
     corrid
    0.50
    Activations Density 1.282%

    No Known Activations