© 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. 2-RES-JB
    11. 9440
    Prev
    Next
    INDEX
    Explanations

    words associated with criticism or strong negative opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ridiculous."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.90
    ribution
    -0.79
    Reviewed
    -0.79
    enfranch
    -0.78
    rien
    -0.78
    emis
    -0.72
    ioch
    -0.71
    itizen
    -0.69
    oyal
    -0.69
    ribut
    -0.68
    POSITIVE LOGITS
     nonsense
    0.94
     absurdity
    0.88
    ishly
    0.83
    nesses
    0.82
     absurd
    0.81
     nonsensical
    0.81
    ness
    0.79
    ulously
    0.77
     amounts
    0.77
     bullshit
    0.75
    Activations Density 0.017%

    No Known Activations