© 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. 15352
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of statements or reports made by organizations or officials

    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
    otin
    -0.91
    ¯¯¯¯
    -0.78
    Roberts
    -0.71
     Cary
    -0.70
     PHI
    -0.70
     dime
    -0.70
     ILCS
    -0.70
     Whitney
    -0.69
    Measure
    -0.69
    Michigan
    -0.68
    POSITIVE LOGITS
     YPG
    0.97
     Ankara
    0.96
     Rouhani
    0.95
     Lavrov
    0.94
    istani
    0.90
     Jakarta
    0.88
     Kurdish
    0.86
     Mohammad
    0.86
     Tehran
    0.85
     Azerbai
    0.84
    Activations Density 0.457%

    No Known Activations