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. 0-RES-JB
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    references to the airline company "Delta."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Delta" and related terms

    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
    mith
    -0.78
    Scotland
    -0.74
    omes
    -0.73
     largeDownload
    -0.72
     disarm
    -0.71
    handed
    -0.70
    tern
    -0.69
     scaff
    -0.69
    urn
    -0.68
    onym
    -0.66
    POSITIVE LOGITS
     Delta
    4.03
    Delta
    3.43
     delta
    2.80
     Gamma
    1.80
     Beta
    1.52
     Eps
    1.48
     Kappa
    1.38
    elta
    1.37
     Alpha
    1.35
     Omega
    1.30
    Activations Density 0.010%

    No Known Activations