Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5432
    Prev
    Next
    INDEX
    Explanations

    web URLs related to articles

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and their content

    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
     level
    -0.70
     rem
    -0.70
     cuff
    -0.70
     zeal
    -0.68
     discretion
    -0.68
     affection
    -0.68
     love
    -0.67
     clos
    -0.65
     master
    -0.65
     control
    -0.64
    POSITIVE LOGITS
    article
    4.42
    articles
    3.29
    Article
    1.59
    chapter
    1.23
    content
    1.22
    products
    1.15
    sections
    1.13
    story
    1.12
    issue
    1.11
    doi
    1.10
    Activations Density 0.019%

    No Known Activations