© 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. 8-RES-JB
    11. 1307
    Prev
    Next
    INDEX
    Explanations

    contractions with the word "in."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in [year]"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.90
    ISC
    -0.82
    orio
    -0.76
    adra
    -0.75
    Oracle
    -0.71
    APH
    -0.71
    imester
    -0.71
    auri
    -0.70
    ãĤ¶
    -0.70
    iosis
    -0.67
    POSITIVE LOGITS
     tha
    0.98
    ',"
    0.90
    selves
    0.89
    '
    0.89
    '?
    0.87
    '-
    0.86
    beard
    0.84
    '.
    0.82
    '"
    0.81
    ',
    0.80
    Activations Density 0.116%

    No Known Activations