© 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. 3-RES-JB
    11. 10777
    Prev
    Next
    INDEX
    Explanations

    references to the country Romania

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Romania

    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
    haw
    -0.79
    oos
    -0.77
    jri
    -0.72
    gets
    -0.71
    owler
    -0.71
    ittle
    -0.71
    roxy
    -0.71
    creen
    -0.71
    oor
    -0.70
    uries
    -0.70
    POSITIVE LOGITS
    arest
    1.06
     Romania
    0.94
     Romanian
    0.91
     Monteneg
    0.90
     Buch
    0.85
     srfAttach
    0.76
     Camer
    0.76
     Falls
    0.75
     Legions
    0.71
     Orthodox
    0.71
    Activations Density 0.005%

    No Known Activations