© 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. 6-RES-JB
    6. 11835
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and innovation

    oai_token-act-pair · gpt-3.5-turbo

    quotations and dialogue markers within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unprotected
    -0.69
     NATO
    -0.65
     retaliation
    -0.64
     constitutionally
    -0.63
     foreign
    -0.62
     assassination
    -0.62
     threatening
    -0.62
     persecut
    -0.61
     Shiite
    -0.61
     assass
    -0.61
    POSITIVE LOGITS
    RESULTS
    0.89
    Results
    0.70
     Designs
    0.69
    Initially
    0.69
    sample
    0.67
    Created
    0.67
    Materials
    0.67
    atography
    0.66
    selage
    0.66
    enture
    0.63
    Activations Density 1.182%

    No Known Activations