© 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. 8-RES-JB
    11. 22395
    Prev
    Next
    INDEX
    Explanations

    words related to inconsistency and issues in behavior or communication

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of continuity and interconnectedness

    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
     NCT
    -0.77
     Bourbon
    -0.70
    wana
    -0.66
     Cheong
    -0.65
    agar
    -0.62
     Benz
    -0.60
    kson
    -0.60
     Willow
    -0.60
    gow
    -0.59
     Gates
    -0.59
    POSITIVE LOGITS
    cled
    0.88
    urate
    0.86
    inence
    0.86
    stantial
    0.79
    uration
    0.78
    urated
    0.76
    rency
    0.75
    cling
    0.74
    ctory
    0.73
    ivable
    0.72
    Activations Density 0.077%

    No Known Activations