© 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. 6-RES-JB
    11. 5115
    Prev
    Next
    INDEX
    Explanations

    action verbs related to causing harm or damage

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to risk assessment and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -0.64
    nen
    -0.58
    ften
    -0.58
    ãĥĥãĥī
    -0.55
    hap
    -0.54
    kos
    -0.53
    urches
    -0.52
    hi
    -0.52
    DAQ
    -0.52
     shoulders
    -0.52
    POSITIVE LOGITS
    lying
    0.65
     thereof
    0.61
     underlying
    0.58
     Accessories
    0.57
     Compare
    0.53
     Description
    0.53
     related
    0.53
     LM
    0.53
     Conclusion
    0.52
     arising
    0.52
    Activations Density 0.990%

    No Known Activations