INDEX

Explanations

comparative phrases or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

<bos>

-0.64

Vidite

-0.57

oredCriteria

-0.55

 للمعارف

-0.49

Numerology

-0.49

 fuite

-0.48

rungsseite

-0.43

 doulou

-0.42

 nasce

-0.42

lə

-0.42

POSITIVE LOGITS

ArgsConstructor

0.70

DoubleQuotes

0.67

RenderAtEndOf

0.66

出版年

0.63

transQ

0.63

AddTagHelper

0.62

SequentialGroup

0.57

 betweenstory

0.55

enumi

0.54

#+#

0.54

Activations Density 1.105%

comparative phrases or concepts

No Comments

No Known Activations