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. 9-RES-JB
    6. 800
    Prev
    Next
    INDEX
    Explanations

    instances where characters such as 'Ļ', 'ă', 'ó', and similar characters are used within the text

    oai_token-act-pair · gpt-3.5-turbo

    specific character strings or punctuation marks that could indicate special formatting or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wonder
    -0.67
     elector
    -0.67
     seiz
    -0.67
     sacrific
    -0.65
     carriers
    -0.65
     partners
    -0.64
     civilian
    -0.63
     carrier
    -0.62
     absentee
    -0.62
     pigeon
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.04
    which
    1.04
    shown
    1.03
    20439
    0.99
    of
    0.94
    above
    0.90
    lished
    0.89
    that
    0.88
    against
    0.87
    ution
    0.86
    Activations Density 0.290%

    No Known Activations