© 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. 11-RES-JB
    11. 7443
    Prev
    Next
    INDEX
    Explanations

    names related to 'Cooper'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cooper" in various contexts

    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
    eric
    -0.76
    enic
    -0.74
    esome
    -0.66
    tags
    -0.65
    tenance
    -0.60
    mable
    -0.60
    ted
    -0.60
    ting
    -0.59
    division
    -0.59
    stals
    -0.59
    POSITIVE LOGITS
    atives
    1.15
    stown
    1.10
    atively
    0.94
    ATIVE
    0.87
    ately
    0.83
    ATURE
    0.80
    ates
    0.75
     Cooper
    0.75
    olly
    0.75
    atures
    0.73
    Activations Density 0.066%

    No Known Activations