© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17358
    Prev
    Next
    INDEX
    Explanations

    words related to specific cases or instances that deviate from a general rule or norm

    oai_token-act-pair · gpt-3.5-turbo

    references to exceptions in rules or guidelines

    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
    yss
    -0.74
    ebus
    -0.74
     istg
    -0.72
    âĸ¬
    -0.71
    riz
    -0.69
    æ©Ł
    -0.68
    Delivery
    -0.65
    legram
    -0.65
     Heist
    -0.65
     Dow
    -0.64
    POSITIVE LOGITS
    poons
    0.93
     exceptions
    0.93
    perty
    0.89
    ervative
    0.86
    ensical
    0.85
    afety
    0.81
    uba
    0.81
    ppings
    0.80
     loopholes
    0.78
    cale
    0.77
    Activations Density 0.010%

    No Known Activations