© 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. 22051
    Prev
    Next
    INDEX
    Explanations

    words related to extreme intensity or strength

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Extreme" and its associated concepts

    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
    Ń·
    -0.88
    allery
    -0.73
    externalActionCode
    -0.70
    Äĩ
    -0.68
    ppo
    -0.68
     veiled
    -0.67
    isSpecialOrderable
    -0.66
    utra
    -0.66
    abet
    -0.65
    hari
    -0.65
    POSITIVE LOGITS
    Extreme
    0.91
    ly
    0.90
     Predator
    0.82
    ITY
    0.81
     Extreme
    0.80
     Championship
    0.78
     Endurance
    0.78
     Solutions
    0.78
    aire
    0.78
     Explorer
    0.77
    Activations Density 0.034%

    No Known Activations