© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13913
    Prev
    Next
    INDEX
    Explanations

    verbs related to searching, investigating, or uncovering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dig" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reilly
    -0.75
    ................................................................
    -0.72
    BuyableInstoreAndOnline
    -0.71
    SAY
    -0.69
     Blueprint
    -0.69
    Kenn
    -0.69
     ACTIONS
    -0.67
    cream
    -0.66
    Thomas
    -0.65
    Ren
    -0.63
    POSITIVE LOGITS
     dig
    1.28
     dug
    1.22
     digs
    1.18
     digging
    1.06
    itial
    0.94
     trenches
    0.90
     Dug
    0.88
    gers
    0.81
    imon
    0.80
    itals
    0.80
    Activations Density 0.006%

    No Known Activations