Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6810
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to fear and courage

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing fear or hesitation to speak out or take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompanied
    -0.80
    >>>>>>>>
    -0.74
    jiang
    -0.72
    marked
    -0.68
    ãĤ¦ãĤ¹
    -0.64
    updated
    -0.63
     largeDownload
    -0.63
    automatic
    -0.62
     Prepar
    -0.62
     determining
    -0.62
    POSITIVE LOGITS
     admit
    1.30
     criticize
    1.24
     speak
    1.22
     defy
    1.17
     confront
    1.15
     pursue
    1.11
     offend
    1.07
     acknowledge
    1.06
     venture
    1.04
     ask
    1.03
    Activations Density 0.120%

    No Known Activations