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. 11-RES-JB
    6. 15334
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Ley" or "ley" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ley" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.86
    efully
    -0.81
    ility
    -0.74
    ILE
    -0.74
    illary
    -0.74
    icist
    -0.72
    acity
    -0.69
    ilers
    -0.69
    eful
    -0.67
    ician
    -0.67
    POSITIVE LOGITS
    wine
    1.01
    rand
    0.97
    Madison
    0.94
    corn
    0.92
    bridge
    0.87
    ton
    0.86
    sburg
    0.84
    wood
    0.83
    ville
    0.81
    croft
    0.81
    Activations Density 0.068%

    No Known Activations