© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    significant numbers or numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and dates

    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
     Silent
    -0.63
    045
    -0.62
    hement
    -0.62
    cott
    -0.60
     Xiaomi
    -0.59
    Drop
    -0.58
    yout
    -0.57
    zinski
    -0.56
    addons
    -0.56
    Austral
    -0.56
    POSITIVE LOGITS
    âĢ²
    0.79
    ourney
    0.74
    hovah
    0.71
    ¢
    0.68
     PAGE
    0.61
    WAY
    0.60
    akedown
    0.57
    ield
    0.56
    ulture
    0.55
    %)
    0.55
    Activations Density 0.235%

    No Known Activations