INDEX

Explanations

references to military actions or conflicts

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

MessageTagHelper

-0.64

shadowRadius

-0.54

日閲覧

-0.49

LookAnd

-0.49

twimg

-0.48

 sagt

-0.45

IconModule

-0.45

iotensin

-0.45

 bilang

-0.44

 typelib

-0.44

POSITIVE LOGITS

 invaded

0.91

 attacked

0.80

 stormed

0.78

 raided

0.75

 besieged

0.73

 entered

0.70

 overwhelmed

0.70

 swar

0.69

 assaulted

0.68

 surrounded

0.67

Activations Density 0.346%

references to military actions or conflicts

No Comments

No Known Activations