© 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. 3-RES-JB
    11. 5692
    Prev
    Next
    INDEX
    Explanations

    references to the TV program "60 Minutes"

    oai_token-act-pair · gpt-3.5-turbo

    references to the television program "60 Minutes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.84
    ilater
    -0.74
    itivity
    -0.71
    ourke
    -0.70
    bid
    -0.69
    ches
    -0.68
    parency
    -0.68
    icult
    -0.67
    sem
    -0.67
    cedes
    -0.67
    POSITIVE LOGITS
     Minutes
    1.27
    Hz
    1.01
     ILCS
    0.99
    fps
    0.91
     Seconds
    0.87
     Hz
    0.84
    625
    0.82
    GW
    0.81
    61
    0.80
    60
    0.80
    Activations Density 0.040%

    No Known Activations