© 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. 10-RES-JB
    11. 4730
    Prev
    Next
    INDEX
    Explanations

    instances where someone is being accused of lying or deception

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "about."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cue
    -0.88
     teasp
    -0.87
    terness
    -0.87
    à¼
    -0.84
    quez
    -0.83
    OGR
    -0.82
    hesis
    -0.79
    KC
    -0.79
    nis
    -0.79
    kie
    -0.75
    POSITIVE LOGITS
     how
    1.16
     why
    0.98
     wanting
    0.98
     whether
    0.96
     needing
    0.93
     reforming
    0.87
     improving
    0.87
     respecting
    0.85
     overcoming
    0.85
     preserving
    0.83
    Activations Density 0.169%

    No Known Activations