© 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. 0-RES-JB
    6. 11267
    Prev
    Next
    INDEX
    Explanations

    words containing the specific pattern "oured" such as "coloured" and "flavoured"

    oai_token-act-pair · gpt-3.5-turbo

    words related to consumption or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Title
    -0.63
     lin
    -0.61
     theater
    -0.60
     Sheldon
    -0.59
     labor
    -0.58
     charism
    -0.58
     credential
    -0.57
     Texas
    -0.57
     Becker
    -0.56
     behavioral
    -0.56
    POSITIVE LOGITS
    oured
    4.39
    ouring
    3.17
    ours
    2.86
    our
    2.32
    OUR
    1.82
    ored
    1.76
    ORED
    1.63
    oring
    1.34
    iour
    1.17
    orer
    1.14
    Activations Density 0.008%

    No Known Activations