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. 961
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and disobedience towards authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal contempt and offenses

    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
    ighed
    -0.82
    illon
    -0.75
     Lumpur
    -0.74
    ·
    -0.72
    pton
    -0.72
    ta
    -0.70
    tted
    -0.70
    alle
    -0.70
    abouts
    -0.70
    ichi
    -0.69
    POSITIVE LOGITS
    uously
    1.10
    uous
    1.07
     charges
    0.78
     lashes
    0.77
    orously
    0.77
     leveled
    0.76
    ously
    0.76
     convictions
    0.76
     writ
    0.75
     contempt
    0.74
    Activations Density 0.041%

    No Known Activations