© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16554
    Prev
    Next
    INDEX
    Explanations

    instances of future plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating plans or intentions

    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
    quickShipAvailable
    -0.73
     Explan
    -0.68
    heit
    -0.66
     Prediction
    -0.66
    listed
    -0.65
    felt
    -0.65
    Sorry
    -0.62
     Leban
    -0.61
    joy
    -0.60
    ected
    -0.60
    POSITIVE LOGITS
     unveil
    1.20
     intensify
    1.12
     retire
    1.11
     revisit
    1.11
     introduce
    1.11
     spend
    1.09
     dedicate
    1.08
     pursue
    1.06
     sue
    1.05
     announce
    1.03
    Activations Density 0.102%

    No Known Activations