© 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. 15681
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express recommendations or opinions about what someone should do

    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
     Fra
    -0.77
    atile
    -0.68
    quickShipAvailable
    -0.67
     Byrd
    -0.61
    anka
    -0.61
     Oss
    -0.61
     deteriorated
    -0.61
     WI
    -0.59
     Hein
    -0.59
     FW
    -0.58
    POSITIVE LOGITS
    nt
    1.13
    ered
    1.11
     be
    1.08
     strive
    0.96
     aspire
    0.95
    n
    0.95
     reconsider
    0.94
     apologise
    0.91
     beware
    0.90
     apologize
    0.89
    Activations Density 0.086%

    No Known Activations