© 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. 17376
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "anti" followed by a subsequent word

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-Semitic sentiments or themes

    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
    mable
    -0.81
    ccording
    -0.77
     tremend
    -0.76
    manship
    -0.72
    doms
    -0.72
    matically
    -0.71
     corrid
    -0.67
     rall
    -0.65
     skelet
    -0.65
     rul
    -0.64
    POSITIVE LOGITS
    anti
    1.09
    ucci
    0.92
     Devi
    0.86
    iso
    0.86
    opsis
    0.85
    zona
    0.84
    qua
    0.82
    pora
    0.78
    oco
    0.78
    ctr
    0.77
    Activations Density 0.013%

    No Known Activations