INDEX

Explanations

phrases related to safety and health concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.50

ar

-0.48

<eos>

-0.47

 Alex

-0.45

vi

-0.45

ček

-0.43

rs

-0.43

si

-0.43

 correspon

-0.43

vo

-0.42

POSITIVE LOGITS

basicConfig

0.98

 itſelf

0.94

 Normdatei

0.91

UnsafeEnabled

0.91

 Мексичка

0.86

GraphicsUnit

0.86

клопе

0.84

 مشين

0.83

expandindo

0.83

 FetchType

0.82

Activations Density 0.500%

phrases related to safety and health concerns

No Comments

No Known Activations