© 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. 8-RES-JB
    11. 2267
    Prev
    Next
    INDEX
    Explanations

    situations where something appears different from reality

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding truthfulness and reality versus perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellaneous
    -0.68
    ablishment
    -0.66
    --+
    -0.62
    Gene
    -0.61
    isable
    -0.60
    Rating
    -0.60
    ileged
    -0.59
     Pwr
    -0.57
     Likes
    -0.57
    onement
    -0.57
    POSITIVE LOGITS
     actually
    1.07
     truth
    1.04
    Actually
    0.98
    actually
    0.97
     reality
    0.94
     Actually
    0.92
    agine
    0.89
     Fraud
    0.80
     actual
    0.79
    truth
    0.78
    Activations Density 0.516%

    No Known Activations