INDEX

Explanations

terms related to personal identification and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ある

-0.72

高い

-0.69

多い

-0.65

 itſelf

-0.64

ConverterFactory

-0.62

あった

-0.61

 myſelf

-0.60

あります

-0.59

ありました

-0.58

 againſt

-0.56

POSITIVE LOGITS

migrationBuilder

0.81

+#+#

0.71

DotNetBar

0.70

tvguidetime

0.68

NewUrlParser

0.65

}`).

0.62

躇

0.62

']=='

0.59

 فريبيس

0.59

Искәрмәләр

0.59

Activations Density 0.016%

terms related to personal identification and verification processes

No Comments

No Known Activations