© 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. 2-RES-JB
    11. 11700
    Prev
    Next
    INDEX
    Explanations

    phrases related to active participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "active" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adra
    -0.78
    aneers
    -0.76
    unts
    -0.76
    umbo
    -0.74
    ageddon
    -0.72
    $$$$
    -0.68
    elf
    -0.68
    OUGH
    -0.68
    yth
    -0.68
    urai
    -0.66
    POSITIVE LOGITS
     active
    1.01
     newsp
    0.88
     participation
    0.84
    active
    0.82
     participant
    0.82
     ingredient
    0.82
     activity
    0.79
     inactive
    0.78
     involvement
    0.78
    activity
    0.74
    Activations Density 0.013%

    No Known Activations