© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    words related to logic, reason, and good judgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rationality and sound judgment

    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
    bered
    -0.79
    another
    -0.76
    aunted
    -0.75
    zona
    -0.71
     downed
    -0.69
    stals
    -0.68
    bearing
    -0.67
    inate
    -0.67
     eliminated
    -0.67
    inates
    -0.66
    POSITIVE LOGITS
    tarian
    1.03
    tarians
    0.82
    \\\\\\\\
    0.82
     enough
    0.81
     partName
    0.81
    mble
    0.77
     sensible
    0.75
    ynes
    0.74
    sonian
    0.72
     commons
    0.70
    Activations Density 0.030%

    No Known Activations