INDEX

Explanations

references to dietary or nutritional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 للاسماء

-0.78

 hObject

-0.74

 surla

-0.71

تقاوى

-0.66

SourceChecksum

-0.65

########.

-0.64

transQ

-0.64

tagHelperRunner

-0.63

 незавершена

-0.61

GraphicsUnit

-0.61

POSITIVE LOGITS

getSub

0.54

csolódó

0.52

0.50

 Jefus

0.49

AndEndTag

0.48

ReusableCell

0.48

 säll

0.47

ipal

0.47

 مرئيه

0.47

lloworld

0.46

Activations Density 1.193%

references to dietary or nutritional information

No Comments

No Known Activations