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. 8-RES-JB
    6. 12008
    Prev
    Next
    INDEX
    Explanations

    instances where something is being moved or returned back to its original position

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ision
    -0.60
    entric
    -0.60
     Newly
    -0.58
    ISION
    -0.57
     Sullivan
    -0.57
     delegation
    -0.56
     viz
    -0.56
     caut
    -0.56
    ises
    -0.54
     understatement
    -0.54
    POSITIVE LOGITS
    packs
    1.15
    fires
    1.11
    dated
    1.08
    fired
    1.06
    wards
    1.04
    doors
    0.98
    lash
    0.97
    tracking
    0.96
    packing
    0.94
    stab
    0.93
    Activations Density 0.059%

    No Known Activations