© 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. 2-RES-JB
    11. 17829
    Prev
    Next
    INDEX
    Explanations

    references to the Middle East

    oai_token-act-pair · gpt-3.5-turbo

    references to the Middle East

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILA
    -0.74
    udeau
    -0.73
    ItemTracker
    -0.73
    gov
    -0.71
    SIGN
    -0.70
    éĹĺ
    -0.68
    illation
    -0.68
    PROV
    -0.67
    lished
    -0.66
    INS
    -0.66
    POSITIVE LOGITS
     Middle
    0.87
     Relief
    0.79
    Middle
    0.77
     School
    0.72
    wich
    0.72
     Arab
    0.72
     Orbit
    0.70
     Quarter
    0.70
     Arabs
    0.69
     Side
    0.68
    Activations Density 0.007%

    No Known Activations