© 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. 4-RES-JB
    11. 7142
    Prev
    Next
    INDEX
    Explanations

    words related to finding flaws or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bottlenecks in processes or systems

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

    No Comments

    Negative Logits
    NOR
    -0.71
     Pwr
    -0.70
     Camel
    -0.69
    eon
    -0.68
    WARD
    -0.63
    MODE
    -0.60
     Laksh
    -0.60
     Mirage
    -0.59
    ctl
    -0.59
    AGES
    -0.59
    POSITIVE LOGITS
    ovo
    1.20
    heed
    0.99
    omore
    0.98
    quist
    0.94
    agog
    0.92
    unci
    0.88
    iency
    0.85
    etics
    0.85
    etsk
    0.84
    ifer
    0.84
    Activations Density 0.006%

    No Known Activations