INDEX

Explanations

phrases related to guidelines or compliance

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

AddTagHelper

-0.75

OGND

-0.71

@"/

-0.66

ẩm

-0.65

Glit

-0.64

ERING

-0.63

HasAnnotation

-0.63

utilisons

-0.62

/******/

-0.61

Rüyada

-0.60

POSITIVE LOGITS

 respect

1.06

 respecto

0.98

respect

0.88

 Respect

0.86

 riguardo

0.80

 respecte

0.77

 RESPECT

0.76

Respect

0.76

 regards

0.74

 respeito

0.73

Activations Density 0.130%

phrases related to guidelines or compliance

No Comments

No Known Activations