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. 4-RES-JB
    6. 17566
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization Hezbollah

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hezbollah

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

    No Comments

    Negative Logits
    juries
    -0.87
    mson
    -0.83
     Jenner
    -0.73
     Scot
    -0.72
    payer
    -0.72
     Nottingham
    -0.70
     Edinburgh
    -0.68
    ownt
    -0.67
     Unreal
    -0.66
    raught
    -0.64
    POSITIVE LOGITS
     operatives
    0.93
     Hezbollah
    0.88
     affiliation
    0.87
     affili
    0.85
     militias
    0.80
     strongh
    0.79
    ollah
    0.77
     fighters
    0.77
     mosqu
    0.76
     dictatorship
    0.76
    Activations Density 0.003%

    No Known Activations