© 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 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. 2-RES-JB
    11. 7085
    Prev
    Next
    INDEX
    Explanations

    text related to official documents and forms ending in 'RE'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "RE" in various contexts

    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
    glers
    -0.82
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
     Indonesian
    -0.73
     Icelandic
    -0.72
    racuse
    -0.71
     Nicarag
    -0.69
     Finnish
    -0.68
     gag
    -0.68
    ãĤ¨ãĥ«
    -0.67
     Kafka
    -0.65
    POSITIVE LOGITS
    LEASE
    1.26
    QUEST
    1.12
    WARD
    1.10
    CLAIM
    1.10
    VERS
    1.10
    ACH
    1.09
    RE
    1.05
    ASON
    1.02
    VIEW
    1.02
    FER
    1.02
    Activations Density 0.008%

    No Known Activations