© 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. 16321
    Prev
    Next
    INDEX
    Explanations

    words related to perfection or imperfection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to perfection and imperfection

    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
    UGH
    -0.79
    OURCE
    -0.77
    cohol
    -0.76
    udeb
    -0.72
    ructose
    -0.71
    ickr
    -0.68
    bane
    -0.67
    IGH
    -0.66
    vernment
    -0.63
    gdala
    -0.63
    POSITIVE LOGITS
    ion
    1.13
    ions
    0.98
    entimes
    0.91
    ly
    0.86
    icles
    0.86
    itude
    0.85
     rall
    0.85
    nesses
    0.84
    ness
    0.79
    imum
    0.78
    Activations Density 0.015%

    No Known Activations