© 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. 7-RES-JB
    11. 9738
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack or scarcity of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of insignificance or minimal impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ser
    -0.68
    ses
    -0.67
    lords
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
    midt
    -0.63
    lation
    -0.63
    agents
    -0.62
    creator
    -0.61
    llers
    -0.61
     Rear
    -0.60
    POSITIVE LOGITS
     else
    0.87
     discern
    0.78
     consolation
    0.78
     rhy
    0.78
     sympathy
    0.73
     fuss
    0.73
     recourse
    0.72
     earthly
    0.71
     inclination
    0.71
     doubt
    0.70
    Activations Density 0.028%

    No Known Activations