© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3476
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations or blame

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accusations or claims related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arton
    -0.79
    cies
    -0.76
    rones
    -0.75
    aic
    -0.72
    rieve
    -0.71
    wayne
    -0.69
    eport
    -0.67
    mentioned
    -0.67
    hen
    -0.66
    tti
    -0.66
    POSITIVE LOGITS
     conspiring
    1.37
     violating
    1.35
     abusing
    1.30
     stealing
    1.27
     committing
    1.27
     favoring
    1.25
     waging
    1.23
     behaving
    1.22
     abandoning
    1.22
     raping
    1.21
    Activations Density 0.060%

    No Known Activations