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. 3-RES-JB
    6. 2123
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and violations

    oai_token-act-pair · gpt-3.5-turbo

    severe violations of human rights and related legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Refresh
    -0.73
    Depth
    -0.72
    Pitt
    -0.71
    peed
    -0.71
     Cary
    -0.70
     Depot
    -0.70
     Boost
    -0.70
     Pittsburgh
    -0.70
     Blizz
    -0.69
    doi
    -0.69
    POSITIVE LOGITS
     murdering
    1.08
     killings
    1.05
     deported
    1.03
     murder
    1.03
     confisc
    1.01
     deport
    1.01
     atrocities
    0.99
     persecuted
    0.98
     offences
    0.93
     persecution
    0.93
    Activations Density 0.544%

    No Known Activations