© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11345
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to political unity and legislative support

    oai_token-act-pair · gpt-3.5-turbo

    references to medical conditions or terms related to reproductive health

    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
    wcs
    -0.89
    Sov
    -0.88
     Sov
    -0.82
     satell
    -0.73
     fert
    -0.69
    interstitial
    -0.68
    Dialogue
    -0.66
     typh
    -0.66
     pestic
    -0.65
    uve
    -0.65
    POSITIVE LOGITS
    omes
    0.75
    ensable
    0.75
    irable
    0.74
    manship
    0.69
    opian
    0.67
    otos
    0.66
    ighty
    0.64
    ateful
    0.64
    ãĤ¡
    0.62
    ements
    0.62
    Activations Density 0.000%

    No Known Activations