© 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. 16606
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ability to improve or take action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can do" in conjunction with expressions of capability or improvement

    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
    ĸļ
    -0.63
    assault
    -0.62
    BuyableInstoreAndOnline
    -0.62
    mes
    -0.61
    IL
    -0.61
    Lenin
    -0.60
    Winged
    -0.59
     showc
    -0.58
    mb
    -0.58
    orious
    -0.56
    POSITIVE LOGITS
     easily
    1.02
     safely
    0.94
     cheaply
    0.89
     comfortably
    0.79
     freely
    0.79
     anywhere
    0.75
    ibly
    0.75
     without
    0.74
     feas
    0.74
     reasonably
    0.74
    Activations Density 0.320%

    No Known Activations