© 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. 11-RES-JB
    11. 22223
    Prev
    Next
    INDEX
    Explanations

    adverbs related to speed or urgency

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rapid change or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHQ
    -0.78
    initely
    -0.76
    chance
    -0.72
    yet
    -0.68
    MIC
    -0.68
    =-=-=-=-=-=-=-=-
    -0.66
    soDeliveryDate
    -0.65
     Sins
    -0.64
    è£ħ
    -0.62
    haps
    -0.62
    POSITIVE LOGITS
     became
    0.90
     dispatched
    0.84
     forgotten
    0.83
     thereafter
    0.83
     transitioned
    0.83
    aneously
    0.82
     dissip
    0.82
     regretted
    0.82
    ened
    0.81
     realised
    0.81
    Activations Density 0.073%

    No Known Activations