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. 9-RES-JB
    6. 10663
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy changes or actions taken under certain circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or organizational policies and regulations

    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
    ospace
    -0.74
    ividual
    -0.65
     frivol
    -0.62
     vulner
    -0.62
    ument
    -0.62
    `
    -0.61
    auga
    -0.60
    okia
    -0.60
    roid
    -0.59
    ascus
    -0.59
    POSITIVE LOGITS
    neath
    1.19
    cuts
    1.05
    lining
    1.04
    pins
    1.03
    lines
    0.97
    lying
    0.96
    mining
    0.95
    stood
    0.92
    stand
    0.91
    performing
    0.90
    Activations Density 0.060%

    No Known Activations