© 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. 6-RES-JB
    11. 17166
    Prev
    Next
    INDEX
    Explanations

    links or calls to action prompting action from the reader, such as clicking, subscribing, or signing up

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest actions or calls to action, particularly those that prompt subscriptions or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.81
     fortun
    -0.67
    ĨĴ
    -0.66
    MpServer
    -0.66
    tests
    -0.64
    quickShipAvailable
    -0.63
     badly
    -0.62
     costing
    -0.62
    cffffcc
    -0.61
    soDeliveryDate
    -0.61
    POSITIVE LOGITS
     avoid
    1.06
     ensure
    1.03
     maximize
    1.02
     encourage
    1.01
     activate
    0.97
     initiate
    0.96
     indicate
    0.94
     get
    0.93
     confirm
    0.93
     learn
    0.91
    Activations Density 0.163%

    No Known Activations