© 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. 7465
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or titles related to individuals

    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
    ModLoader
    -0.66
     hindsight
    -0.62
     clubhouse
    -0.61
    LEASE
    -0.57
    ãĤ¨ãĥ«
    -0.52
     symbolism
    -0.52
     interchangeable
    -0.51
     Wolves
    -0.51
     equivalents
    -0.51
     undecided
    -0.51
    POSITIVE LOGITS
    inski
    0.87
    ovich
    0.83
    mann
    0.82
    enberg
    0.78
    stad
    0.78
    auer
    0.77
    ich
    0.76
    ensen
    0.76
    endor
    0.75
     (@
    0.73
    Activations Density 0.765%

    No Known Activations