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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 10626
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific company or organization, specifically one represented by the letters "AN."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.83
    Magikarp
    -0.70
    Wheel
    -0.69
    Neigh
    -0.68
     Clancy
    -0.68
     Tycoon
    -0.66
     Brach
    -0.66
    bugs
    -0.66
    glers
    -0.65
    ï¸ı
    -0.64
    POSITIVE LOGITS
    OTHER
    1.02
    IST
    0.99
    onym
    0.97
    omal
    0.94
    alyses
    0.92
    alysed
    0.90
    alys
    0.90
    onymous
    0.89
    terior
    0.87
    alogue
    0.87
    Activations Density 0.007%

    No Known Activations