© 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. 3020
    Prev
    Next
    INDEX
    Explanations

    terms related to actions taken in response to certain situations, usually involving authority or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to legal issues or controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    conserv
    -0.90
    ÙĴ
    -0.90
    iably
    -0.87
    fortunately
    -0.87
    vertising
    -0.84
    entimes
    -0.83
    Examples
    -0.82
    ogether
    -0.82
    #$#$
    -0.81
    ãĥĦ
    -0.81
    POSITIVE LOGITS
     probe
    1.01
     latest
    0.88
     Latest
    0.86
     feds
    0.85
     aftermath
    0.84
     NYT
    0.83
     IPO
    0.79
     Kavanaugh
    0.79
     pope
    0.78
     exodus
    0.78
    Activations Density 0.503%

    No Known Activations