© 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. 3-RES-JB
    11. 7255
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that frequently contain the word "of."

    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
    pret
    -0.70
    =]
    -0.68
    ħĭ
    -0.68
    acus
    -0.62
    let
    -0.61
    mas
    -0.60
    rine
    -0.59
     Rabb
    -0.58
    bet
    -0.58
    System
    -0.58
    POSITIVE LOGITS
     entries
    0.73
     sorts
    0.70
     consecutive
    0.67
     positives
    0.67
     allowable
    0.67
     occurrences
    0.66
     installments
    0.65
     interesting
    0.64
     dollars
    0.64
     Nations
    0.64
    Activations Density 0.153%

    No Known Activations