© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Mali"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the country Mali and related geographical names

    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
    ×Ļ×
    -0.89
    ellation
    -0.83
    IAL
    -0.81
    irlf
    -0.77
    Ö¼
    -0.74
    ä½ľ
    -0.73
     ballpark
    -0.71
    Jane
    -0.71
    VERTISEMENT
    -0.68
    ×
    -0.68
    POSITIVE LOGITS
     Mali
    1.22
    pas
    0.84
    mint
    0.80
     Senegal
    0.80
     Malta
    0.78
     Maurit
    0.78
    ouf
    0.77
     Niger
    0.77
    wan
    0.77
    uth
    0.76
    Activations Density 0.009%

    No Known Activations