INDEX

Explanations

phrases or commands that indicate restrictions or prohibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

zzleHttp

-0.77

ValueStyle

-0.77

ContentLoaded

-0.71

+#+#

-0.71

 <<<<<<<<<<<<<<

-0.67

-0.66

Hozzáférés

-0.64

ApiModelProperty

-0.64

ۜ

-0.64

новништво

-0.63

POSITIVE LOGITS

any

0.78

or

0.65

 anything

0.61

any

0.60

ANY

0.59

nor

0.57

čios

0.57

Any

0.56

 nenhum

0.55

 anywhere

0.55

Activations Density 0.409%

phrases or commands that indicate restrictions or prohibitions

No Comments

No Known Activations