© 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. 4-RES-JB
    11. 6894
    Prev
    Next
    INDEX
    Explanations

    specific locations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and notable events

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

    No Comments

    Negative Logits
    enegger
    -0.53
     Vaugh
    -0.52
    hovah
    -0.51
    rily
    -0.49
    ALSE
    -0.47
    Lago
    -0.45
    theless
    -0.45
    ocrates
    -0.43
    èĢ
    -0.43
    thia
    -0.42
    POSITIVE LOGITS
     movement
    0.59
     lineup
    0.58
     franchise
    0.51
     Initiative
    0.50
     umbrella
    0.50
    ndum
    0.50
     community
    0.49
     initiative
    0.49
     debacle
    0.48
    vernment
    0.47
    Activations Density 1.688%

    No Known Activations