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. 6-RES-JB
    6. 8175
    Prev
    Next
    INDEX
    Explanations

    phrases related to memorization or memory in texts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to memory and memorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRO
    -0.70
    roxy
    -0.69
     Simulator
    -0.69
    OHN
    -0.68
     Prometheus
    -0.64
    ulhu
    -0.60
    Conclusion
    -0.59
     Bourbon
    -0.59
     methane
    -0.58
     Silk
    -0.58
    POSITIVE LOGITS
    abilia
    1.78
    ably
    1.13
    andum
    1.09
    ographed
    1.02
    ific
    1.00
     memor
    0.99
    ized
    0.99
    icol
    0.98
    istically
    0.97
    brance
    0.95
    Activations Density 0.009%

    No Known Activations