© 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. 23574
    Prev
    Next
    INDEX
    Explanations

    words related to mysticism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mystery and mysticism

    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
    ¶ħ
    -0.71
    ©¶æ
    -0.67
    alez
    -0.66
    wark
    -0.65
    anchester
    -0.65
     sacked
    -0.63
    PER
    -0.62
     Sutton
    -0.61
     Whedon
    -0.61
     Winchester
    -0.60
    POSITIVE LOGITS
    ique
    1.17
    ics
    0.95
    adel
    0.94
    ifications
    0.93
    ically
    0.92
    iques
    0.91
    algia
    0.88
    rics
    0.85
    ère
    0.84
    ulously
    0.83
    Activations Density 0.021%

    No Known Activations