© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22676
    Prev
    Next
    INDEX
    Explanations

    comparisons between two entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or contrasts between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    collar
    -0.90
    erie
    -0.89
    erb
    -0.86
    emouth
    -0.83
    lev
    -0.83
    red
    -0.82
    wik
    -0.81
    oder
    -0.81
    yright
    -0.81
    elle
    -0.81
    POSITIVE LOGITS
     versus
    0.74
     nil
    0.74
     Versus
    0.71
     mindset
    0.69
     portfolios
    0.67
     virginity
    0.67
     situational
    0.66
     shenan
    0.64
     scissors
    0.64
     Advantage
    0.64
    Activations Density 0.007%

    No Known Activations