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

    Neuronpedia

    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. 20891
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts that are fundamentally important or flawed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize foundational aspects or differences

    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
    ries
    -0.75
     Commissioners
    -0.69
     Chronicle
    -0.68
    tein
    -0.67
     supervisors
    -0.65
     Purchase
    -0.64
     Supervisor
    -0.64
     Guys
    -0.63
     runners
    -0.63
     Maid
    -0.62
    POSITIVE LOGITS
     differentiated
    0.86
    00007
    0.80
     altering
    0.77
     restruct
    0.76
     wedd
    0.74
     disrupting
    0.73
    gebra
    0.73
     housed
    0.72
     embodied
    0.71
    ascript
    0.71
    Activations Density 0.011%

    No Known Activations