© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    percentages represented in the text

    oai_token-act-pair · gpt-3.5-turbo

    percentage values and their representations

    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
    bies
    -0.64
    spr
    -0.62
    zek
    -0.62
    ãĤ©
    -0.62
    çīĪ
    -0.61
    ãĥ¤
    -0.60
     altern
    -0.59
    pecially
    -0.59
     dile
    -0.59
    Ne
    -0.57
    POSITIVE LOGITS
    bps
    0.85
    xual
    0.83
    luster
    0.80
    factor
    0.79
    uality
    0.75
    uation
    0.74
    %.
    0.72
    alyst
    0.72
    iffe
    0.70
    asin
    0.69
    Activations Density 0.073%

    No Known Activations