© 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. 4-RES-JB
    11. 10703
    Prev
    Next
    INDEX
    Explanations

    phrases related to online activity, such as "Offline Activity" or "Member Activity" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances and references to physical activity

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

    No Comments

    Negative Logits
    gling
    -0.80
    oiler
    -0.68
    ãĥĥãĥĪ
    -0.66
    uran
    -0.65
    agar
    -0.65
     Nak
    -0.64
    enthal
    -0.64
     veiled
    -0.63
    ×Ļ×
    -0.61
     vengeance
    -0.60
    POSITIVE LOGITS
     activity
    0.92
     Activity
    0.90
    activity
    0.85
    ional
    0.77
    pmwiki
    0.77
    iveness
    0.75
     tracker
    0.74
    nesota
    0.72
    nels
    0.71
    uated
    0.71
    Activations Density 0.015%

    No Known Activations