© 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. 1-RES-JB
    11. 3756
    Prev
    Next
    INDEX
    Explanations

    terms related to unethical or exploitative behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to profanity and unethical behavior

    oai_token-act-pair · gpt-3.5-turbo
    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
    empty
    -0.77
    warm
    -0.75
    wolves
    -0.75
    20439
    -0.74
    forth
    -0.72
    ment
    -0.68
    MENTS
    -0.67
    WAY
    -0.67
    WAYS
    -0.66
    DAY
    -0.65
    POSITIVE LOGITS
     prof
    1.41
     mathemat
    1.02
     thous
    0.95
    luent
    0.92
    licted
    0.89
    eatures
    0.88
     predec
    0.87
    inances
    0.85
    essor
    0.84
     concess
    0.83
    Activations Density 0.006%

    No Known Activations