© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 774
    Prev
    Next
    INDEX
    Explanations

    the name "Drew"

    oai_token-act-pair · gpt-4-turbo

    phrases or names related to the name "Drew."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Drew."

    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
    ãĤ³
    -0.92
    ãĥķãĤ©
    -0.76
    ãĤ±
    -0.76
     Gamergate
    -0.72
    ãĤ¿
    -0.71
    ãĤ¹ãĥĪ
    -0.68
    ãĥ´ãĤ¡
    -0.67
    CHO
    -0.67
    Enlarge
    -0.66
     Labour
    -0.65
    POSITIVE LOGITS
     Brees
    1.03
    bles
    0.91
    nesday
    0.89
     Carey
    0.85
    bled
    0.84
    bling
    0.82
    erek
    0.79
     Drew
    0.78
    lett
    0.77
    illo
    0.74
    Activations Density 0.004%

    No Known Activations