© 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. 12060
    Prev
    Next
    INDEX
    Explanations

    commands or requests to stop doing something

    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
    orthy
    -0.82
    ridge
    -0.77
    ocene
    -0.77
    eer
    -0.77
    ãĤĬ
    -0.73
    essee
    -0.72
    aceae
    -0.72
    Sov
    -0.71
    dds
    -0.71
    rocket
    -0.69
    POSITIVE LOGITS
     bothering
    1.38
     wasting
    1.22
     worrying
    1.19
     pretending
    1.14
     whining
    1.11
     messing
    1.10
     caring
    1.09
     behaving
    1.06
     talking
    1.02
     abusing
    1.02
    Activations Density 0.041%

    No Known Activations