© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21113
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent actions and confrontations involving multiple individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to violent or aggressive incidents involving groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.74
    ãĤ´ãĥ³
    -0.72
     Comprehensive
    -0.71
    ISTORY
    -0.70
     successes
    -0.68
     taxpayers
    -0.68
    immune
    -0.65
     waterways
    -0.64
     reinstated
    -0.62
     virtues
    -0.62
    POSITIVE LOGITS
    looking
    0.94
     resembling
    0.83
     approached
    0.82
     wielding
    0.80
     dressed
    0.79
     approaching
    0.75
    nikov
    0.73
     masked
    0.73
     unidentified
    0.72
     barg
    0.72
    Activations Density 0.436%

    No Known Activations