© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of excavating or searching deeply

    oai_token-act-pair · gpt-3.5-turbo

    the term "dig," particularly in various forms and contexts

    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
    BuyableInstoreAndOnline
    -0.77
     Blueprint
    -0.73
     ACTIONS
    -0.72
     Karin
    -0.68
     Peninsula
    -0.67
     Mara
    -0.66
     Gamble
    -0.65
     Rae
    -0.64
     Rebellion
    -0.64
     Russo
    -0.63
    POSITIVE LOGITS
    imon
    1.11
    gers
    1.06
    itial
    1.05
    ression
    1.01
    itals
    0.99
    Dig
    0.98
    itized
    0.98
    raph
    0.97
    itiz
    0.96
    ging
    0.96
    Activations Density 0.007%

    No Known Activations