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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 15227
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical altercations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of violent confrontations or struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uably
    -0.72
    etheless
    -0.69
    ocally
    -0.65
    iterranean
    -0.63
     honoured
    -0.62
     inher
    -0.62
    女
    -0.61
     EDITION
    -0.61
    çīĪ
    -0.60
     descendants
    -0.59
    POSITIVE LOGITS
     startled
    0.78
     panicked
    0.71
     takedown
    0.68
     gunfire
    0.64
    Stop
    0.63
    Suddenly
    0.63
     unconscious
    0.63
     hurried
    0.61
     agitated
    0.61
     grabbed
    0.61
    Activations Density 1.018%

    No Known Activations