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. 0-RES-JB
    6. 14298
    Prev
    Next
    INDEX
    Explanations

    words related to retrieving or retrieval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data retrieval and memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.87
    mares
    -0.81
     Zionism
    -0.81
    ihad
    -0.78
    ihar
    -0.75
    leness
    -0.72
    erity
    -0.71
    ulent
    -0.70
    ensions
    -0.69
     Palestine
    -0.69
    POSITIVE LOGITS
     retrieved
    1.23
     Internet
    0.88
     internet
    0.84
     retri
    0.77
    Internet
    0.68
    RFC
    0.67
     retrieval
    0.67
     prospective
    0.66
     mating
    0.65
     archaeological
    0.65
    Activations Density 0.003%

    No Known Activations