© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12863
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Ja"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or names

    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
    sworth
    -0.84
    ships
    -0.81
    grounds
    -0.76
    sheet
    -0.75
    balance
    -0.70
    Catal
    -0.70
    rified
    -0.70
    thumbnails
    -0.68
    Interstitial
    -0.68
    mate
    -0.67
    POSITIVE LOGITS
    ja
    1.15
    quez
    0.94
    ques
    0.93
    Å¡
    0.87
    ñ
    0.87
    udeau
    0.87
    ivas
    0.86
    ishi
    0.84
    zyk
    0.84
    ë
    0.83
    Activations Density 0.008%

    No Known Activations