INDEX

Explanations

classifications and ratings related to products or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 INTERESAR

-0.63

 OFDb

-0.62

تقاوى

-0.58

;#

-0.57

帖最后由

-0.57

MethodManager

-0.56

dymyr

-0.54

CDATA

-0.53

CloseOperation

-0.53

 nawr

-0.52

POSITIVE LOGITS

 Level

0.83

Level

0.77

 level

0.74

 Tier

0.73

 LEVEL

0.70

plevel

0.70

level

0.68

 livello

0.67

lvl

0.65

LEVEL

0.65

Activations Density 0.305%

classifications and ratings related to products or entities

No Comments

No Known Activations