© 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. 18825
    Prev
    Next
    INDEX
    Explanations

    phrases related to the present moment

    oai_token-act-pair · gpt-3.5-turbo

    references to the current time or urgency

    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
     Shards
    -0.60
     Rewards
    -0.56
     Ammunition
    -0.54
     Rack
    -0.53
     Supply
    -0.53
     Airl
    -0.52
     misfortune
    -0.51
    é¾
    -0.51
     ZIP
    -0.51
     Gupta
    -0.50
    POSITIVE LOGITS
    adays
    1.48
    here
    1.24
    abouts
    1.05
    heres
    0.98
    tical
    0.87
    tics
    0.81
    orthy
    0.78
    that
    0.76
    heric
    0.75
    itia
    0.75
    Activations Density 0.070%

    No Known Activations