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. 17015
    Prev
    Next
    INDEX
    Explanations

    terms related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that denote existence or presence

    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
    ocracy
    -0.75
     unfocusedRange
    -0.72
    iew
    -0.67
    ographer
    -0.66
    ocaust
    -0.65
    gow
    -0.64
    inav
    -0.63
    afety
    -0.63
    ioch
    -0.62
    teness
    -0.62
    POSITIVE LOGITS
     respectively
    1.43
     trademarks
    1.22
     mutually
    1.12
     alike
    1.11
     examples
    1.08
     jointly
    1.03
     staples
    1.00
     both
    1.00
     fronts
    0.99
     pillars
    0.98
    Activations Density 0.233%

    No Known Activations