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. 1-RES-JB
    6. 17575
    Prev
    Next
    INDEX
    Explanations

    keyboard commands indicated by greater than sign followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    commands or actions related to menu options and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iqueness
    -1.10
    etheless
    -0.93
     destro
    -0.92
    onite
    -0.90
    acies
    -0.87
    onial
    -0.85
    ilogy
    -0.83
    erville
    -0.83
    undai
    -0.78
    ascus
    -0.78
    POSITIVE LOGITS
    _>
    1.50
     >
    1.18
    -->
    1.01
    =>
    0.91
    .<
    0.91
    >
    0.90
    ++++++++
    0.88
    âĸ¬âĸ¬
    0.86
    ++++
    0.86
     ><
    0.85
    Activations Density 0.010%

    No Known Activations