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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 2603
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Lebanon

    oai_token-act-pair · gpt-3.5-turbo

    references to Lebanon and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vich
    -0.81
    lasses
    -0.77
    ointed
    -0.77
    uristic
    -0.76
    gers
    -0.74
    earable
    -0.74
    haw
    -0.73
    oted
    -0.73
    ramid
    -0.70
    ierrez
    -0.69
    POSITIVE LOGITS
     Lebanon
    0.82
     Hezbollah
    0.79
     Beirut
    0.74
     Plain
    0.72
    ites
    0.70
     ILCS
    0.70
     Lebanese
    0.70
    isi
    0.69
     Leban
    0.67
    igon
    0.63
    Activations Density 0.024%

    No Known Activations