© 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. 3-RES-JB
    11. 9274
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named Araragi

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.80
    iculty
    -0.76
    ¬¼
    -0.76
    ãĤ´ãĥ³
    -0.74
    stakes
    -0.71
    ãģį
    -0.69
    eners
    -0.68
    HAEL
    -0.67
    sylvania
    -0.66
    hower
    -0.64
    POSITIVE LOGITS
    ithmetic
    0.99
    beit
    0.97
    issa
    0.96
    thritis
    0.93
    ign
    0.93
    ansas
    0.93
    leigh
    0.92
    leys
    0.90
    ranging
    0.88
    isen
    0.87
    Activations Density 0.008%

    No Known Activations