INDEX

Explanations

punctuation marks at the end of sentences and questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

PYX

-0.74

Спољашње

-0.61

ніципалі

-0.61

 Савезне

-0.61

хьтан

-0.59

GraphicsUnit

-0.58

 Trinit

-0.57

 ویکی‌پدیا

-0.57

췄

-0.55

شهاد

-0.55

POSITIVE LOGITS

↵↵

1.48

↵

0.95

</h3>

0.79

↵↵↵

0.78

</strong>

0.72

</h4>

0.69

</blockquote>

0.67

</h2>

0.62

//};

0.60

</h5>

0.59

Activations Density 0.559%

punctuation marks at the end of sentences and questions

No Comments

No Known Activations