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. 7-RES-JB
    6. 464
    Prev
    Next
    INDEX
    Explanations

    references to the Egyptian pyramids

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "py" related to various contexts or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ously
    -0.92
    worthiness
    -0.71
    nesota
    -0.71
    iveness
    -0.68
    ï¸
    -0.65
    itism
    -0.65
    DERR
    -0.65
    ï¸ı
    -0.65
    ciating
    -0.64
     Rockefeller
    -0.64
    POSITIVE LOGITS
    ramids
    1.41
    ramid
    1.37
    ongyang
    1.21
    rote
    1.09
    gments
    0.94
    romancer
    0.91
    rites
    0.91
    Py
    0.90
    ersen
    0.88
    rene
    0.86
    Activations Density 0.024%

    No Known Activations