INDEX

Explanations

phrases indicating completeness or totality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ReusableCell

-0.86

#+#

-0.83

ModelAdmin

-0.78

存于互联网档案馆

-0.76

**/

-0.74

Tikang

-0.73

tvguidetime

-0.72

ganet

-0.69

ⓧ

-0.68

 /*#__

-0.66

POSITIVE LOGITS

All

0.92

All

0.89

all

0.65

all

0.63

ALL

0.59

 essentially

0.58

 prices

0.57

 invariably

0.52

 normally

0.52

 always

0.50

Activations Density 0.123%

phrases indicating completeness or totality

No Comments

No Known Activations