© 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. 11-RES-JB
    11. 17378
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or advocating for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expressing and amplifying one's voice and opinions

    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
     Reincarn
    -0.81
     sequence
    -0.66
     Trip
    -0.63
     scenery
    -0.62
     Scenes
    -0.61
     conjunction
    -0.60
    ivably
    -0.60
     Carbuncle
    -0.60
     Sequence
    -0.60
     Refresh
    -0.59
    POSITIVE LOGITS
     louder
    1.43
     voices
    1.36
     voice
    1.23
    voice
    1.21
     loud
    1.18
     Voices
    1.16
     heard
    1.10
     voiced
    1.09
     voicing
    1.09
     dissenting
    1.04
    Activations Density 0.093%

    No Known Activations