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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15909
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, often focusing on convictions

    oai_token-act-pair · gpt-3.5-turbo

    instances of people being convicted of crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mentation
    -0.61
    Secure
    -0.58
    ENTION
    -0.56
    clips
    -0.55
    ANS
    -0.55
    ãģĦ
    -0.54
    ecd
    -0.54
    sit
    -0.53
    ffee
    -0.52
    EEP
    -0.52
    POSITIVE LOGITS
     of
    1.05
     felon
    0.96
     thereof
    0.94
    of
    0.85
     guilty
    0.84
     sentenced
    0.81
     rapist
    0.81
     convict
    0.79
     fel
    0.79
     murderer
    0.74
    Activations Density 0.061%

    No Known Activations