© 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. 628
    Prev
    Next
    INDEX
    Explanations

    phrases related to redoing or repeating actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to reopening or resuming activities, particularly in a governance or procedural context

    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
    elo
    -0.61
     protr
    -0.59
    aley
    -0.59
     Lily
    -0.56
     upfront
    -0.55
    Weather
    -0.54
     semic
    -0.54
     Huntington
    -0.53
    ello
    -0.53
     abundantly
    -0.53
    POSITIVE LOGITS
    issance
    1.36
    itory
    0.98
    xual
    0.97
    owship
    0.91
    ction
    0.90
    burse
    0.81
    ctions
    0.81
    ndum
    0.81
    quit
    0.80
    spective
    0.79
    Activations Density 0.056%

    No Known Activations