© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 8353
    Prev
    Next
    INDEX
    Explanations

    expressions related to expressing strong emotions or opinions, often in a negative or critical way

    oai_token-act-pair · gpt-3.5-turbo

    words related to rants and tirades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undai
    -0.85
    earances
    -0.80
    existent
    -0.69
    rity
    -0.68
    pleting
    -0.68
    licts
    -0.67
    ccording
    -0.67
    negie
    -0.67
     acquisitions
    -0.66
    earned
    -0.65
    POSITIVE LOGITS
     rant
    1.20
     tir
    1.14
     aloud
    0.86
    ings
    0.78
     loudly
    0.73
     outburst
    0.72
    urous
    0.68
     against
    0.68
    ifest
    0.68
     angrily
    0.67
    Activations Density 0.017%

    No Known Activations