INDEX

Explanations

relationships and comparisons within 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 @ 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

awtextra

-0.67

modb

-0.53

 חיצוניים

-0.52

getMinutes

-0.51

LookAnd

-0.48

 createState

-0.47

дового

-0.44

 Normdatei

-0.42

까지

-0.41

 विश्वसनीयता

-0.41

POSITIVE LOGITS

 same

3.21

same

3.09

Same

2.90

 Same

2.67

 mismo

2.34

 SAME

2.31

 samma

2.28

 mesma

2.27

 misma

2.27

 dezelfde

2.26

Activations Density 0.667%

relationships and comparisons within the text

No Comments

No Known Activations