© 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. 7537
    Prev
    Next
    INDEX
    Explanations

    dates and author names in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    the presence of attributions or citations in the text

    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
    ĸļ
    -0.90
    rons
    -0.85
    ifts
    -0.78
    enance
    -0.75
    ippi
    -0.74
    raints
    -0.73
    ifting
    -0.73
    inkle
    -0.72
     Beir
    -0.72
    orical
    -0.71
    POSITIVE LOGITS
    cffff
    1.11
     |--
    0.98
    ··
    0.83
     +---
    0.72
     |
    0.72
    âĢ¢âĢ¢
    0.71
    ////////////////////////////////
    0.70
    Mah
    0.70
     EntityItem
    0.69
     grep
    0.68
    Activations Density 0.017%

    No Known Activations