© 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. 9-RES-JB
    11. 6953
    Prev
    Next
    INDEX
    Explanations

    political figures' names and states in the context of news snippets

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses in the text

    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
     rave
    -0.81
     smugglers
    -0.80
     intrinsic
    -0.73
     ransom
    -0.73
     compilation
    -0.71
     stabil
    -0.69
     infring
    -0.69
     customs
    -0.68
     blasp
    -0.68
     extras
    -0.67
    POSITIVE LOGITS
    pictured
    1.23
    whose
    1.18
    who
    1.18
    Republican
    1.15
    Fla
    1.12
    formerly
    1.08
    Calif
    1.05
    Va
    1.03
    Ohio
    1.03
    Wisconsin
    1.03
    Activations Density 0.041%

    No Known Activations