INDEX

Explanations

phrases indicating conflict or opposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 يتيمه

-0.47

[]:

-0.47

unner

-0.44

AssignableFrom

-0.43

htbp

-0.43

いる

-0.42

 المعيارى

-0.42

avení

-0.41

 îles

-0.41

iastical

-0.40

POSITIVE LOGITS

 reputations

0.74

 fortunes

0.69

 InputDecoration

0.68

 noses

0.66

GEBURTSDATUM

0.66

 electricity

0.66

 onView

0.65

 glaciers

0.65

 ArrayAdapter

0.65

SequentialGroup

0.64

Activations Density 0.324%

phrases indicating conflict or opposition

No Comments

No Known Activations