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. 2-RES-JB
    6. 161
    Prev
    Next
    INDEX
    Explanations

    the word "cynical"

    oai_token-act-pair · gpt-4-turbo

    words related to cynicism

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with cynicism and disillusionment

    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
    ĸļ
    -0.85
    erto
    -0.78
    acid
    -0.77
    upon
    -0.76
    byter
    -0.74
    ymes
    -0.73
    amins
    -0.72
    upload
    -0.72
    Interstitial
    -0.72
    edited
    -0.70
    POSITIVE LOGITS
     cyn
    0.96
     observer
    0.76
     cynicism
    0.74
     overlook
    0.74
     cynical
    0.74
    sters
    0.73
     Cyn
    0.71
     ploy
    0.69
    aneers
    0.67
     chic
    0.66
    Activations Density 0.013%

    No Known Activations