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. 9691
    Prev
    Next
    INDEX
    Explanations

    specific articles discussing different topics or contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal phrases or time indicators

    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
    meal
    -0.66
    ragon
    -0.62
    folios
    -0.61
    buster
    -0.61
    onet
    -0.61
    zu
    -0.59
    Jar
    -0.59
    marine
    -0.59
    Loading
    -0.59
    Je
    -0.58
    POSITIVE LOGITS
     sake
    1.35
     purposes
    1.11
    icion
    1.03
     reasons
    1.00
     instance
    0.87
     Reasons
    0.83
     meantime
    0.82
     example
    0.80
     unin
    0.73
     avoidance
    0.72
    Activations Density 0.090%

    No Known Activations