© 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. 17821
    Prev
    Next
    INDEX
    Explanations

    phrases related to erratic behavior and mental instability

    oai_token-act-pair · gpt-3.5-turbo

    references to psychological or emotional states and behaviors

    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
    keyes
    -0.73
    ction
    -0.72
    otin
    -0.68
     respective
    -0.67
    riad
    -0.67
    addons
    -0.66
    ISS
    -0.65
    Available
    -0.64
    oor
    -0.63
    Remove
    -0.61
    POSITIVE LOGITS
     himself
    1.16
     Himself
    0.90
     herself
    0.84
     his
    0.82
     His
    0.81
     wandered
    0.80
     enjoys
    0.79
     evidently
    0.79
    His
    0.78
     confessed
    0.77
    Activations Density 1.002%

    No Known Activations