INDEX

Explanations

terms and elements related to structured data and user interface components

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)");

-1.02

)";

-0.98

.";

-0.97

"]);

-0.90

`;

-0.88

NUMX

-0.87

.",

-0.85

."));

-0.82

']);

-0.80

。】

-0.78

POSITIVE LOGITS

</

0.85

0.71

</th>

0.68

</h2>

0.67

0.66

</td>

0.64

0.63

0.61

\\

0.61

\'

0.60

Activations Density 0.253%

terms and elements related to structured data and user interface components

No Comments

No Known Activations