© 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. 775
    Prev
    Next
    INDEX
    Explanations

    present tense verbs relating to progression or change

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to gaining or increasing 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
    oha
    -0.72
    croft
    -0.72
    eka
    -0.72
    ooting
    -0.71
    peria
    -0.71
    shared
    -0.70
    oot
    -0.70
    bal
    -0.69
    aura
    -0.67
    cia
    -0.66
    POSITIVE LOGITS
     steadily
    0.86
     awfully
    0.85
     increasingly
    0.80
     pains
    0.79
     dangerously
    0.78
     steady
    0.70
     upwards
    0.70
     inex
    0.69
     breaths
    0.69
     restless
    0.68
    Activations Density 0.386%

    No Known Activations