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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    6. 17823
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and agreements, specifically focusing on terms like "ETA" and "TMZ"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "ETA" and the acronym "TMZ"

    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
    nian
    -0.81
    mar
    -0.76
    nen
    -0.72
    shr
    -0.70
    hip
    -0.69
    ugal
    -0.69
    rab
    -0.69
    bar
    -0.67
    shire
    -0.67
    space
    -0.67
    POSITIVE LOGITS
    CHAT
    1.14
    ILS
    1.02
    IRED
    0.95
     IMAGES
    0.89
    ETA
    0.84
    ICE
    0.84
    ISE
    0.83
    ILE
    0.81
    IL
    0.81
    BIL
    0.80
    Activations Density 0.014%

    No Known Activations