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. 11-RES-JB
    6. 10382
    Prev
    Next
    INDEX
    Explanations

    legal and criminal terms related to charges and accusations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violent crimes and legal charges

    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
     trickle
    -0.67
    Nav
    -0.66
    Reviewer
    -0.64
    ROM
    -0.63
     opio
    -0.62
    opa
    -0.62
    Grad
    -0.61
    \":
    -0.61
     rethink
    -0.59
     mull
    -0.59
    POSITIVE LOGITS
     stemming
    1.15
     manslaughter
    1.09
     punishable
    1.07
     causing
    1.04
     aggravated
    1.02
     offences
    0.98
     offenses
    0.95
     inflicting
    0.93
     felony
    0.89
     arising
    0.88
    Activations Density 0.128%

    No Known Activations