© 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. 10-RES-JB
    11. 4886
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of programmatic prevention and reduction initiatives, such as crime prevention plans, traffic calming measures, pollution reduction standards, etc

    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
    omsky
    -0.87
    imeo
    -0.84
    rez
    -0.84
    lished
    -0.83
    join
    -0.75
    yip
    -0.75
     Forsaken
    -0.75
    eworld
    -0.74
    pload
    -0.74
    sey
    -0.73
    POSITIVE LOGITS
     measures
    1.55
     programmes
    1.35
     strategies
    1.35
     initiatives
    1.32
     programs
    1.30
     efforts
    1.29
     procedures
    1.24
     techniques
    1.22
     activities
    1.20
     Measures
    1.20
    Activations Density 0.245%

    No Known Activations