INDEX

Explanations

references to specific entities or nouns 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

parametrize

-0.64

NameInMap

-0.62

WebElementEntity

-0.58

SuppressLint

-0.57

cokinetic

-0.56

antMatchers

-0.53

̍t

-0.52

NOOP

-0.52

doi

-0.52

drawString

-0.52

POSITIVE LOGITS

 FROM

1.27

FROM

1.26

 from

1.10

from

1.05

 From

1.04

 från

1.04

From

1.02

getFrom

0.92

 từ

0.91

จาก

0.86

Activations Density 0.163%

references to specific entities or nouns in the text

No Comments

No Known Activations