© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 22488
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the name "Cooper"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Cooper."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rely
    -0.69
    enic
    -0.64
    seeing
    -0.63
    chal
    -0.60
    IAS
    -0.60
    ħĭ
    -0.57
    ted
    -0.57
    eric
    -0.57
     Judgment
    -0.57
     editors
    -0.57
    POSITIVE LOGITS
     Cooper
    1.20
    stown
    0.97
    atives
    0.85
    icker
    0.83
    lear
    0.82
    ature
    0.79
    ately
    0.79
    atum
    0.78
     cooper
    0.76
    ATURE
    0.75
    Activations Density 0.010%

    No Known Activations