© 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. 10-RES-JB
    11. 8575
    Prev
    Next
    INDEX
    Explanations

    references to physical harm or damage

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liam
    -0.79
    atari
    -0.77
     Democr
    -0.69
    ugi
    -0.65
     seldom
    -0.64
     unden
    -0.62
     Millenn
    -0.61
     ende
    -0.61
    zhen
    -0.60
     perpetually
    -0.60
    POSITIVE LOGITS
     nor
    1.18
     wrongdoing
    1.07
     harmed
    1.03
     anything
    1.02
     anybody
    0.93
     whatsoever
    0.91
    threatening
    0.89
    anything
    0.89
     any
    0.88
     anyone
    0.87
    Activations Density 0.360%

    No Known Activations