© 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. 16066
    Prev
    Next
    INDEX
    Explanations

    names of people and their corresponding statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    dialogue or conversational exchanges 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
     reapp
    -0.76
     probing
    -0.72
     awaits
    -0.68
     displaced
    -0.63
     reasoned
    -0.63
     forgotten
    -0.63
     contag
    -0.63
     pont
    -0.62
     stranded
    -0.61
     repro
    -0.61
    POSITIVE LOGITS
    Absolutely
    1.37
    Yeah
    1.27
    Honestly
    1.19
    Probably
    1.19
    Well
    1.17
     Yeah
    1.16
    Yes
    1.16
     Honestly
    1.14
    Laughs
    1.13
     Absolutely
    1.13
    Activations Density 0.147%

    No Known Activations