© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17770
    Prev
    Next
    INDEX
    Explanations

    countries or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to Tunisia and related geographic entities

    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
    croft
    -0.92
    bilt
    -0.87
    loss
    -0.79
    alach
    -0.78
    lasses
    -0.74
    effic
    -0.73
    mble
    -0.72
    ving
    -0.72
    rint
    -0.71
    place
    -0.66
    POSITIVE LOGITS
     Tunis
    0.96
     Tunisia
    0.93
     Tanz
    0.88
     Airways
    0.81
    etta
    0.80
    ophobia
    0.79
    essa
    0.77
    ienne
    0.76
     Mubarak
    0.75
    ophobic
    0.74
    Activations Density 0.012%

    No Known Activations