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. 13147
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns describing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    sentiments related to strong emotions and preferences

    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
     helicop
    -0.73
    mans
    -0.66
    err
    -0.66
    conduct
    -0.63
     stages
    -0.62
    ghazi
    -0.62
    gow
    -0.62
    hematically
    -0.60
    engers
    -0.60
     Appendix
    -0.60
    POSITIVE LOGITS
    lessness
    0.89
     toward
    0.89
     towards
    0.83
    rence
    0.80
    iness
    0.77
     thirst
    0.77
    itiveness
    0.76
     aroused
    0.76
    acy
    0.75
     fascination
    0.73
    Activations Density 0.152%

    No Known Activations