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. 7-RES-JB
    6. 1016
    Prev
    Next
    INDEX
    Explanations

    phrases related to triumph or dominance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "trumping" or negating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fellow
    -0.69
     Publisher
    -0.66
     rehab
    -0.64
    URI
    -0.63
    raq
    -0.61
    Gamer
    -0.61
     Relief
    -0.61
     alienation
    -0.61
     Reconstruction
    -0.61
     Underground
    -0.60
    POSITIVE LOGITS
    eting
    1.24
    xual
    1.11
    stakes
    0.94
    resent
    0.92
    ets
    0.90
    eter
    0.84
    eded
    0.83
     trump
    0.83
    eters
    0.83
    ighed
    0.79
    Activations Density 0.043%

    No Known Activations