INDEX

Explanations

sentences with complex or nuanced logical structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

NewUrlParser

-0.96

yntaxException

-0.89

 Audiodateien

-0.81

 myſelf

-0.79

 تضيفلها

-0.78

SOUNDBITE

-0.77

PreAuthorize

-0.75

Sklici

-0.72

providedIn

-0.72

ToBounds

-0.71

POSITIVE LOGITS

 Ebenso

0.57

ibal

0.53

Aholisi

0.52

Inter

0.49

but

0.49

 Wire

0.48

 Inter

0.48

WIRE

0.48

其

0.47

Count

0.47

Activations Density 0.377%

sentences with complex or nuanced logical structure

No Comments

No Known Activations