INDEX

Explanations

indicators of technical documentation or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.73

↵

-0.68

↵↵↵

-0.65

↵↵

-0.65

↵↵↵↵

-0.63

UnknownFieldSet

-0.61

 مشين

-0.60

↵↵↵↵↵

-0.55

__":

-0.55

LikeLike

-0.54

POSITIVE LOGITS

^(@)

0.67

躇

0.62

 tslint

0.60

mobileqq

0.59

forChild

0.59

&'

0.58

Rüyada

0.58

 Мексичка

0.57

'/',

0.57

 IndexPath

0.56

Activations Density 0.272%

indicators of technical documentation or specifications

No Comments

No Known Activations