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. 6-RES-JB
    6. 16530
    Prev
    Next
    INDEX
    Explanations

    words related to intense anger or frustration

    oai_token-act-pair · gpt-3.5-turbo

    expressions and references to rage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 6 - anger

    No Comments

    Negative Logits
    metics
    -0.86
    ramer
    -0.82
    herty
    -0.79
    icut
    -0.76
    ablished
    -0.73
    itions
    -0.72
    roma
    -0.67
    ococ
    -0.67
     pse
    -0.67
     delegation
    -0.67
    POSITIVE LOGITS
    quit
    1.04
     raging
    0.88
     rage
    0.85
     fury
    0.83
     mad
    0.80
     raged
    0.78
    naire
    0.78
     furnace
    0.78
     outburst
    0.75
     against
    0.75
    Activations Density 0.024%

    No Known Activations