© 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. 7-RES-JB
    11. 23866
    Prev
    Next
    INDEX
    Explanations

    keywords related to time and events

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating presence or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iggins
    -0.72
    idon
    -0.70
    arat
    -0.58
    leground
    -0.58
    ²¾
    -0.57
    ultan
    -0.57
    ioch
    -0.56
    cise
    -0.55
     Kills
    -0.55
    xual
    -0.55
    POSITIVE LOGITS
     bets
    0.67
    ":""},{"
    0.67
    inventoryQuantity
    0.62
     analysts
    0.62
     engineers
    0.55
     automakers
    0.54
     observers
    0.53
    steamapps
    0.53
     developers
    0.52
    çĶ°
    0.52
    Activations Density 0.408%

    No Known Activations