Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17391
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documentation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "UM."

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

    No Comments

    Negative Logits
    alty
    -0.70
    ãĥ¼ãĤ¯
    -0.66
     rift
    -0.64
    zzi
    -0.62
    ttes
    -0.62
    rette
    -0.61
    ighter
    -0.61
     otherwise
    -0.60
    issance
    -0.60
    ãĥĥ
    -0.60
    POSITIVE LOGITS
    MER
    1.16
    UM
    1.07
    BLE
    1.06
    MY
    1.01
    UL
    0.90
    ENTS
    0.89
    ITS
    0.89
    BUS
    0.87
    BER
    0.86
    ULT
    0.86
    Activations Density 0.013%

    No Known Activations