INDEX

Explanations

repeated phrases or patterns in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

väg

-0.41

ASA

-0.40

そうです

-0.39

といけない

-0.38

 Könige

-0.37

INTERNAL

-0.37

 opérés

-0.37

chymal

-0.37

윤

-0.36

 even

-0.36

POSITIVE LOGITS

libft

0.64

RTLD

0.63

wpi

0.62

 Vikipedi

0.62

typeorm

0.60

دانشنامهٔ

0.60

 Normdatei

0.59

potent

0.59

JNIEnv

0.59

 oprot

0.58

Activations Density 0.093%

repeated phrases or patterns in the text

No Comments

No Known Activations