© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    words related to enhancing, increasing, or improving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an increase or enhancement

    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
    ©¶æ
    -0.89
     Lange
    -0.74
    viol
    -0.72
    rors
    -0.66
     flaw
    -0.64
     Sins
    -0.62
    bryce
    -0.62
     Hague
    -0.62
     Frie
    -0.61
    iott
    -0.61
    POSITIVE LOGITS
     morale
    1.16
     productivity
    0.94
     efficiency
    0.93
     enthusiasm
    0.85
     boost
    0.83
     competitiveness
    0.80
     turnout
    0.80
     spirits
    0.80
     uptake
    0.79
     sales
    0.79
    Activations Density 0.066%

    No Known Activations