© 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. 11-RES-JB
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    individuals who have been through certain experiences or programs

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups in a variety of contexts

    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
    Translation
    -0.74
    Sharp
    -0.70
     Anyway
    -0.67
     Lets
    -0.67
    Reading
    -0.65
     Bound
    -0.63
    Hope
    -0.62
    "]=>
    -0.61
    Anyway
    -0.61
    Magikarp
    -0.60
    POSITIVE LOGITS
     underwent
    1.16
     weren
    1.16
     participated
    1.12
     were
    1.11
     hadn
    1.11
     died
    1.04
     lacked
    1.02
     received
    1.02
    've
    1.02
     aren
    1.00
    Activations Density 0.132%

    No Known Activations