© 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. 10-RES-JB
    11. 6366
    Prev
    Next
    INDEX
    Explanations

    phrases related to a lack of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roo
    -0.84
    aroo
    -0.81
    minus
    -0.79
    Ń·
    -0.78
    dan
    -0.76
    hog
    -0.72
    hov
    -0.71
    nard
    -0.70
    arte
    -0.70
    ername
    -0.69
    POSITIVE LOGITS
     clarity
    1.24
     transparency
    1.19
     enthusiasm
    1.14
     accountability
    1.11
     responsiveness
    1.09
     specificity
    1.08
     sophistication
    1.07
     awareness
    1.07
     adequate
    1.06
     confidence
    1.06
    Activations Density 0.072%

    No Known Activations