© 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. 9-RES-JB
    11. 10149
    Prev
    Next
    INDEX
    Explanations

    words related to plans or actions that are set to be carried out in the future

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" indicating future events or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sickness
    -0.71
    luck
    -0.69
     Pictures
    -0.69
     Whats
    -0.69
     innocence
    -0.65
    intent
    -0.63
     Melody
    -0.63
     scares
    -0.63
    ilver
    -0.62
    idences
    -0.61
    POSITIVE LOGITS
     overseen
    1.16
     implemented
    1.10
     phased
    1.10
     distributed
    1.07
     unveiled
    1.07
     reviewed
    1.06
     evaluated
    1.02
     administered
    1.01
     financed
    0.99
     monitored
    0.97
    Activations Density 0.155%

    No Known Activations