Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16248
    Prev
    Next
    INDEX
    Explanations

    descriptions of people or characters along with a particular physical attribute

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe people or objects accompanied by specific attributes or actions

    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
    Merit
    -0.80
     Provided
    -0.73
    estate
    -0.70
    ICO
    -0.70
    FW
    -0.70
    Poll
    -0.67
    iversal
    -0.67
     hereafter
    -0.66
    hower
    -0.64
    here
    -0.64
    POSITIVE LOGITS
    stood
    1.46
    drawn
    1.27
    draw
    1.08
     clenched
    1.02
     sunglasses
    1.01
     goggles
    1.00
     headphones
    0.99
     electrodes
    0.98
     scissors
    0.97
     horns
    0.96
    Activations Density 0.148%

    No Known Activations