© 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. 2-RES-JB
    11. 9121
    Prev
    Next
    INDEX
    Explanations

    sophisticated and articulate language and expressions

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to effective communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aples
    -0.72
    avis
    -0.72
    ulhu
    -0.69
     disadvant
    -0.68
    finder
    -0.67
    FactoryReloaded
    -0.66
    apolis
    -0.64
    ploma
    -0.64
    omorphic
    -0.63
    WAYS
    -0.62
    POSITIVE LOGITS
    ly
    1.09
    ness
    0.97
     eloqu
    0.85
    liness
    0.79
    itude
    0.78
    forward
    0.75
     succinct
    0.73
    bly
    0.71
    oire
    0.70
    mented
    0.69
    Activations Density 0.014%

    No Known Activations