© 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. 3-RES-JB
    11. 6212
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of something being heavily involved or regulated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "heavily" indicating significant intensity or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.92
    iry
    -0.80
     Thumbnails
    -0.77
    atu
    -0.71
    SCP
    -0.68
    scl
    -0.67
     Chaser
    -0.67
     Parables
    -0.66
     Marriage
    -0.66
     Kids
    -0.66
    POSITIVE LOGITS
     subsid
    0.92
     concentrated
    0.87
     enough
    0.82
     subsidized
    0.80
     reliant
    0.80
     marketed
    0.79
     oxid
    0.79
     relied
    0.79
     influenced
    0.78
     armoured
    0.78
    Activations Density 0.012%

    No Known Activations