INDEX

Explanations

instances of specific formatting or coding markers

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

 المعيارى

-0.71

UIControlState

-0.64

chum

-0.56

 createSlice

-0.56

\}\\

-0.55

 Frei

-0.54

CodeAttribute

-0.54

qquad

-0.54

гава

-0.53

all

-0.52

POSITIVE LOGITS

YE

1.36

Yud

1.28

YM

1.28

YR

1.27

Yel

1.25

YP

1.25

Yom

1.25

Yew

1.23

YAP

1.22

Yaz

1.21

Activations Density 0.323%

instances of specific formatting or coding markers

No Comments

No Known Activations