© 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. 17784
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person named "Mul"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mul" in various contexts

    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
     Continued
    -0.79
     Physicians
    -0.72
     Featured
    -0.72
     Eleven
    -0.71
     Hurricanes
    -0.71
     Whole
    -0.71
     Rossi
    -0.71
     Competitive
    -0.68
     LIMITED
    -0.67
     Helsinki
    -0.67
    POSITIVE LOGITS
    igans
    1.06
     Mul
    1.00
    iple
    0.98
    enium
    0.92
    aney
    0.92
    aroo
    0.91
    rats
    0.89
    icides
    0.88
    cair
    0.87
    umber
    0.86
    Activations Density 0.005%

    No Known Activations