© 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. 10-RES-JB
    11. 970
    Prev
    Next
    INDEX
    Explanations

    years in the format of 20YY

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.71
    pora
    -0.71
    plom
    -0.70
    ochet
    -0.67
    hei
    -0.66
    urat
    -0.65
    kell
    -0.61
    osal
    -0.60
    ño
    -0.59
    ilic
    -0.58
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.19
    committee
    0.97
    th
    0.95
    48
    0.89
    40
    0.88
    200000
    0.87
    97
    0.84
    26
    0.84
    XX
    0.84
    %
    0.82
    Activations Density 0.071%

    No Known Activations