INDEX

Explanations

programming-related logical operations and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

En

-0.49

en

-0.49

↵↵

-0.48

 Even

-0.47

Even

-0.47

log

-0.46

ς

-0.46

RenderAtEndOf

-0.45

 alles

-0.42

[],

-0.42

POSITIVE LOGITS

EDEFAULT

0.93

+#+#

0.86

 оригіналу

0.85

enumi

0.84

Xna

0.79

تقاوى

0.75

 незавершена

0.75

equalTo

0.72

Tembelea

0.72

 pageContext

0.71

Activations Density 0.226%

programming-related logical operations and comparisons

No Comments

No Known Activations