INDEX

Explanations

hashtag symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

openConnection

-0.52

kusen

-0.50

aarrggbb

-0.50

GeneratedMessage

-0.47

audrait

-0.47

webElement

-0.47

ništvo

-0.47

strip

-0.45

posób

-0.44

ozat

-0.43

POSITIVE LOGITS

0.91

;->

0.78

MemoryWarning

0.76

__["

0.72

offsetof

0.71

antMatchers

0.71

 مرئيه

0.68

Демографія

0.68

yntaxException

0.66

WebVitals

0.66

Activations Density 0.035%

hashtag symbols

No Comments

No Known Activations