© 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. 9-RES-JB
    11. 20872
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms related to contracts, pricing, and technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or terms related to measurements and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Large
    -0.82
    Nap
    -0.79
    Ann
    -0.78
    Natural
    -0.78
    Dust
    -0.78
    Slow
    -0.78
    Lost
    -0.77
    Comb
    -0.76
    Ak
    -0.76
    Normal
    -0.76
    POSITIVE LOGITS
     slate
    0.85
     brethren
    0.80
     status
    0.80
     bandwagon
    0.79
     counterpart
    0.78
     candidacy
    0.78
     device
    0.75
     counterparts
    0.75
     platform
    0.74
     jumper
    0.73
    Activations Density 0.357%

    No Known Activations