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. 10-RES-JB
    6. 15210
    Prev
    Next
    INDEX
    Explanations

    numerical data such as figures and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to significant financial investments or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pistons
    -0.88
    Detroit
    -0.87
    Putin
    -0.85
     Detroit
    -0.83
    andowski
    -0.82
    Moscow
    -0.82
     Kremlin
    -0.80
     Dmit
    -0.79
    Denver
    -0.77
    arnaev
    -0.77
    POSITIVE LOGITS
     Auckland
    2.20
     Kiw
    2.09
    NZ
    1.97
     NZ
    1.97
    uckland
    1.87
     Wellington
    1.73
     Fiji
    1.71
     Zealand
    1.60
     Samoa
    1.56
     Hawai
    1.55
    Activations Density 0.228%

    No Known Activations