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. 2849
    Prev
    Next
    INDEX
    Explanations

    terms related to naming rights

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "naming" and related terms in contexts discussing rights or policies

    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
    hematic
    -0.79
    otropic
    -0.75
     Towns
    -0.70
    iere
    -0.68
    ECD
    -0.68
     Highly
    -0.64
     prec
    -0.64
    gui
    -0.62
    imester
    -0.60
    Cu
    -0.60
    POSITIVE LOGITS
     conventions
    0.99
    plates
    0.96
     naming
    0.95
     convention
    0.94
    alogy
    0.86
    uez
    0.85
     ceremonies
    0.82
    ames
    0.82
     attribution
    0.80
    paces
    0.78
    Activations Density 0.012%

    No Known Activations