© 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. 2-RES-JB
    11. 21291
    Prev
    Next
    INDEX
    Explanations

    the word "al" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "al."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EntityItem
    -0.81
    displayText
    -0.78
     Chaser
    -0.77
    SourceFile
    -0.76
    FFER
    -0.73
    ĸļ
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.71
    soDeliveryDate
    -0.68
    Chip
    -0.67
    éĹĺ
    -0.65
    POSITIVE LOGITS
    axy
    1.07
    abama
    1.01
    ogical
    1.00
     Pradesh
    0.98
    endar
    0.97
    gorith
    0.96
    ibaba
    0.95
    oha
    0.94
    ayer
    0.93
    ibur
    0.91
    Activations Density 0.038%

    No Known Activations