© 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. 12645
    Prev
    Next
    INDEX
    Explanations

    capitalized sequences of letters that spell out "OL" followed by a number from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or entity, indicated by the repeated acronym "OL"

    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
     Citizen
    -0.76
    ãĥ¥
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.71
    ãĥĥãĥī
    -0.68
    ãĥ¼ãĥĨ
    -0.68
     Empires
    -0.67
    ãĥ¯ãĥ³
    -0.67
    ãĥ£
    -0.66
    ãĤ¢ãĥ«
    -0.66
     Hiroshima
    -0.66
    POSITIVE LOGITS
    VIDIA
    1.10
    ipop
    1.10
    ibrary
    1.02
    OL
    1.01
    atile
    1.00
    anguage
    0.96
    ateral
    0.96
    onial
    0.95
    aptop
    0.94
    OAD
    0.94
    Activations Density 0.008%

    No Known Activations