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. 2-RES-JB
    6. 19279
    Prev
    Next
    INDEX
    Explanations

    words related to spoilage, ruining, or damaging

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of spoiling or negative transformations

    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
    jriwal
    -0.79
    arettes
    -0.76
    aida
    -0.71
    ajo
    -0.71
    ickr
    -0.68
     practitioner
    -0.67
    ribune
    -0.67
    rouch
    -0.66
    odynamic
    -0.66
     lobbying
    -0.66
    POSITIVE LOGITS
     spo
    1.51
     spoil
    1.49
     spoiled
    0.98
     Spo
    0.93
     rotten
    0.84
    Thumbnail
    0.76
     appet
    0.76
    arding
    0.72
    stan
    0.70
    --+
    0.70
    Activations Density 0.011%

    No Known Activations