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. 9-RES-JB
    6. 153
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and drinks

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks that denote the conclusion of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retracted
    -0.78
     exit
    -0.77
     extinguished
    -0.77
     rupture
    -0.73
     sacked
    -0.73
     displaced
    -0.73
     resc
    -0.71
     attrition
    -0.70
     accuser
    -0.70
     casualty
    -0.70
    POSITIVE LOGITS
     Anyway
    1.55
    Anyway
    1.47
     Needless
    1.40
     Recently
    1.32
     Personally
    1.30
     Therefore
    1.24
     However
    1.21
     Unfortunately
    1.20
     Basically
    1.20
     Interestingly
    1.20
    Activations Density 0.564%

    No Known Activations