© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20780
    Prev
    Next
    INDEX
    Explanations

    personal reactions or emotional responses

    oai_token-act-pair · gpt-3.5-turbo

    references to engagement and audience reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utor
    -0.78
    tesy
    -0.74
    aband
    -0.72
    »Ĵ
    -0.70
    adiq
    -0.68
     subcontract
    -0.66
    onduct
    -0.65
     Pastebin
    -0.64
    MSN
    -0.64
    idable
    -0.63
    POSITIVE LOGITS
     itching
    1.34
     buzzing
    1.31
     wondering
    1.28
     laughing
    1.27
     excited
    1.25
     intrigued
    1.25
     goose
    1.24
     scratching
    1.20
     craving
    1.15
     longing
    1.15
    Activations Density 0.195%

    No Known Activations