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. 7-RES-JB
    6. 16352
    Prev
    Next
    INDEX
    Explanations

    phrases related to being challenged or in conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confront" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aku
    -0.73
    erd
    -0.72
    serving
    -0.71
    cott
    -0.70
    estate
    -0.70
    elled
    -0.70
    urt
    -0.69
    head
    -0.69
    stream
    -0.67
    amba
    -0.66
    POSITIVE LOGITS
     encounters
    0.75
    ational
    0.75
     confront
    0.73
     Metatron
    0.71
    idable
    0.71
    ienced
    0.69
     insur
    0.69
    ãĥķ
    0.69
     confronting
    0.68
     Triangle
    0.67
    Activations Density 0.048%

    No Known Activations