© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    verbs related to producing or sharing information publicly

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of publishing

    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
    uana
    -0.84
    imir
    -0.75
    akia
    -0.71
    ichael
    -0.71
    enhagen
    -0.68
    ibur
    -0.68
    llan
    -0.68
     Lanka
    -0.68
     Antar
    -0.68
    xa
    -0.67
    POSITIVE LOGITS
    lishing
    1.17
    lisher
    1.14
    lishes
    1.11
     publish
    0.80
     publishes
    0.77
    л
    0.75
     excerpts
    0.74
     publishing
    0.74
     calendars
    0.71
    published
    0.70
    Activations Density 0.028%

    No Known Activations