© 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. 7509
    Prev
    Next
    INDEX
    Explanations

    characters in different languages

    oai_token-act-pair · gpt-3.5-turbo

    symbols and non-standard characters

    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
    awaru
    -1.02
     Flavoring
    -0.90
    merce
    -0.88
    nings
    -0.85
     contrace
    -0.83
     mathemat
    -0.76
    ciating
    -0.75
    kef
    -0.73
     simultane
    -0.73
     richness
    -0.73
    POSITIVE LOGITS
    ãĤ¡
    1.09
    ر
    0.89
    ople
    0.83
    ι
    0.82
    inx
    0.79
    ¹
    0.77
    ħ
    0.77
    а
    0.76
    era
    0.75
    ´
    0.74
    Activations Density 0.004%

    No Known Activations