Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18094
    Prev
    Next
    INDEX
    Explanations

    texts related to a specific event or location, specifically mentioning the term "Kerbal"

    oai_token-act-pair · gpt-3.5-turbo

    words related to imbalance and balance issues

    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
     DRAG
    -0.74
     Gutenberg
    -0.70
    IPP
    -0.70
    CRIP
    -0.69
     ROS
    -0.68
     Pix
    -0.68
    ktop
    -0.67
     MET
    -0.67
     Met
    -0.66
     Rabbit
    -0.66
    POSITIVE LOGITS
    veyard
    0.91
    bably
    0.91
    etheless
    0.89
    istic
    0.88
    isky
    0.88
    istically
    0.87
    ition
    0.85
    interstitial
    0.81
    thood
    0.81
    hari
    0.79
    Activations Density 0.012%

    No Known Activations