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. 10-RES-JB
    6. 293
    Prev
    Next
    INDEX
    Explanations

    phrases related to revisiting, rehashing, and rethinking various topics, including events, ideas, and concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to re-evaluation or transformation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.77
    mpeg
    -0.66
    aila
    -0.66
    respond
    -0.61
    vertisement
    -0.60
    bara
    -0.60
    oko
    -0.60
    iyah
    -0.60
    osher
    -0.60
     increase
    -0.59
    POSITIVE LOGITS
     old
    0.91
     Memories
    0.87
     memories
    0.85
     classics
    0.84
     fond
    0.72
     stale
    0.72
     defunct
    0.68
    ITED
    0.67
     Magicka
    0.67
     dormant
    0.66
    Activations Density 0.191%

    No Known Activations