© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to viewership statistics

    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
    warts
    -0.92
    ances
    -0.74
    icka
    -0.74
    krit
    -0.70
    erity
    -0.68
     simplicity
    -0.68
    allel
    -0.68
    arest
    -0.67
     tremend
    -0.67
    emate
    -0.66
    POSITIVE LOGITS
     è£ıè¦ļéĨĴ
    0.98
     crore
    0.96
    gp
    0.89
    000
    0.88
     000
    0.85
     Hz
    0.85
    0002
    0.85
    Hz
    0.84
    mAh
    0.81
    644
    0.80
    Activations Density 0.061%

    No Known Activations