INDEX

Explanations

mentions of attacks and aggressive actions

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

{~

-0.73

 թվական

-0.72

Ав

-0.69

nO

-0.68

 км

-0.62

 مرئيه

-0.62

setOnItem

-0.61

ുന്നു

-0.61

uros

-0.61

└

-0.61

POSITIVE LOGITS

 Attack

2.33

 attack

2.30

 ATTACK

2.17

 attacks

2.16

attack

2.12

 Attacks

2.07

Attack

2.01

Attacks

2.00

ATTACK

1.99

attacks

1.90

Activations Density 0.047%

mentions of attacks and aggressive actions

No Comments

No Known Activations