© 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. 19811
    Prev
    Next
    INDEX
    Explanations

    adjectives related to capability or potential

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of achieving maximum outcomes or efficiency

    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
    mare
    -0.78
    masters
    -0.74
    gar
    -0.72
    eries
    -0.71
    riad
    -0.70
    erie
    -0.70
    mens
    -0.70
    yer
    -0.67
    ¡
    -0.65
    ĪĴ
    -0.63
    POSITIVE LOGITS
     without
    0.69
     beforehand
    0.65
     before
    0.65
    iary
    0.64
     achievable
    0.63
     avoided
    0.63
     è£ıè
    0.63
     BEFORE
    0.61
     whilst
    0.60
     practicable
    0.60
    Activations Density 0.042%

    No Known Activations