© 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. 3-RES-JB
    6. 15567
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "enough."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enough" suggesting sufficient quantity or adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guth
    -0.75
    amon
    -0.74
     Myster
    -0.66
     quo
    -0.63
    cul
    -0.63
    ificate
    -0.62
    folk
    -0.62
    chet
    -0.62
    bull
    -0.61
    men
    -0.60
    POSITIVE LOGITS
    osponsors
    0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.68
     dstg
    0.66
     ILCS
    0.65
    inventoryQuantity
    0.65
    itbart
    0.64
    -+-+
    0.63
    azaki
    0.61
     sidx
    0.60
    rehend
    0.60
    Activations Density 0.027%

    No Known Activations