© 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. 6-RES-JB
    11. 13608
    Prev
    Next
    INDEX
    Explanations

    names or terms related to Arabic regions or culture

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'q'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESA
    -0.65
     Lauder
    -0.65
     Oblivion
    -0.63
     readable
    -0.62
    ufact
    -0.62
     hect
    -0.62
    FTWARE
    -0.60
     savior
    -0.59
     irrad
    -0.59
     FANT
    -0.59
    POSITIVE LOGITS
    eus
    0.97
    iu
    0.97
    edo
    0.92
    ees
    0.92
    aeda
    0.91
    dn
    0.90
    arth
    0.89
    iao
    0.87
    uably
    0.86
    iji
    0.84
    Activations Density 0.018%

    No Known Activations