© 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. 12668
    Prev
    Next
    INDEX
    Explanations

    words related to historical figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to notable historical or public figures, particularly those with the name "Nikola" and others associated with significant contributions or controversies

    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
    pmwiki
    -0.83
    anguage
    -0.82
    iking
    -0.74
     tiss
    -0.71
    creen
    -0.71
     Skydragon
    -0.70
     externalToEVAOnly
    -0.69
    cloth
    -0.68
    irtual
    -0.67
    aver
    -0.67
    POSITIVE LOGITS
    dinand
    0.96
    WER
    0.87
    ï¸
    0.84
    Sov
    0.77
    olph
    0.77
    Ľ
    0.74
    rax
    0.73
    =-=-
    0.73
    orically
    0.68
    Ĥ¬
    0.68
    Activations Density 0.032%

    No Known Activations