© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9036
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of something being unfiltered or unaltered

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "filtered" and its related forms

    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
     Fey
    -0.65
    ANA
    -0.62
    raised
    -0.61
    Found
    -0.60
    Plug
    -0.59
     modeled
    -0.58
    Solution
    -0.57
     Helpful
    -0.57
     pronounced
    -0.56
    Problem
    -0.56
    POSITIVE LOGITS
    tered
    1.04
    tering
    0.87
    mie
    0.82
    culosis
    0.80
    cules
    0.80
    iated
    0.77
    redd
    0.77
    enium
    0.76
    bling
    0.76
    med
    0.75
    Activations Density 0.010%

    No Known Activations