© 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. 15694
    Prev
    Next
    INDEX
    Explanations

    words related to expressing personal opinions and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating honesty or directness in communication

    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
     backdrop
    -0.75
     retreating
    -0.73
     ransom
    -0.72
     unden
    -0.69
     dissolve
    -0.63
     enshr
    -0.63
    coming
    -0.58
    §
    -0.57
     strand
    -0.56
     arise
    -0.56
    POSITIVE LOGITS
     NEVER
    0.88
     ROCK
    0.75
     amazed
    0.70
     ain
    0.70
     THANK
    0.69
     LOVE
    0.68
    ZI
    0.65
     impressed
    0.64
     neither
    0.64
     nobody
    0.64
    Activations Density 0.236%

    No Known Activations