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. 8-RES-JB
    6. 4500
    Prev
    Next
    INDEX
    Explanations

    Adjectives and verbs describing negative emotions and actions

    oai_token-act-pair · gpt-3.5-turbo

    themes of conflict and societal challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illin
    -0.72
    Dispatch
    -0.70
     Entered
    -0.68
    Tes
    -0.64
    azaki
    -0.64
    Fla
    -0.61
    oga
    -0.60
     marrow
    -0.60
    Reviewed
    -0.60
     Vaughan
    -0.57
    POSITIVE LOGITS
     refers
    0.83
     huh
    0.83
     encompasses
    0.81
    Reviewer
    0.80
     NEVER
    0.76
    ertodd
    0.76
     nonetheless
    0.73
     itself
    0.73
     ALWAYS
    0.73
     entails
    0.72
    Activations Density 1.058%

    No Known Activations