© 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. 7-RES-JB
    11. 5369
    Prev
    Next
    INDEX
    Explanations

    personal habits and behavioral patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to habits and patterns in behaviors or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otropic
    -0.78
    Lens
    -0.77
    POSE
    -0.75
    thouse
    -0.71
    birth
    -0.70
    Slot
    -0.70
    car
    -0.69
    INAL
    -0.67
    MG
    -0.67
    Īè
    -0.65
    POSITIVE LOGITS
     coincide
    0.73
    etter
    0.72
     fluct
    0.71
     vary
    0.70
     dictates
    0.69
     dictated
    0.68
     dictate
    0.68
     quo
    0.67
    etting
    0.66
    changed
    0.65
    Activations Density 0.259%

    No Known Activations