INDEX

Explanations

references to identification and passport-related documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 >=",

-0.97

 betweenstory

-0.90

parsedMessage

-0.89

Билгалдахарш

-0.78

 BoxFit

-0.78

ⓧ

-0.75

LookAnd

-0.73

 Paglinawan

-0.72

ValueStyle

-0.70

География

-0.69

POSITIVE LOGITS

 card

0.72

 passport

0.70

 issued

0.67

 cards

0.67

card

0.63

 Passport

0.59

 Pass

0.58

ID

0.56

Passport

0.55

 visa

0.54

Activations Density 0.161%

references to identification and passport-related documentation

No Comments

No Known Activations