INDEX

Explanations

elements related to user accounts and verification processes, particularly in a social media context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 تضيفلها

-1.04

IVEREF

-0.85

 itſelf

-0.80

 greateſt

-0.79

tvguidetime

-0.79

 виправивши

-0.78

 Mahomet

-0.76

 himo

-0.76

帖最后由

-0.75

 Catholicism

-0.74

POSITIVE LOGITS

cre

0.63

PositiveButton

0.62

ro

0.60

me

0.57

tij

0.56

ca

0.54

zkod

0.54

Sar

0.52

ret

0.52

pic

0.52

Activations Density 0.168%

elements related to user accounts and verification processes, particularly in a social media context

No Comments

No Known Activations