INDEX

Explanations

terms related to weapons and their utilization or categorization

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 مشين

-0.87

LabelTagHelper

-0.80

setVerticalGroup

-0.78

STC

-0.77

Boiling

-0.77

 lynx

-0.76

 pageContext

-0.74

 hoort

-0.74

 ujednoznacz

-0.73

OrNil

-0.73

POSITIVE LOGITS

 weapons

2.20

 weapon

2.06

 Weapon

1.84

 Weapons

1.81

weapon

1.81

weapons

1.81

Weapons

1.59

Weapon

1.57

 weaponry

1.45

WEAPON

1.29

Activations Density 0.076%

terms related to weapons and their utilization or categorization

No Comments

No Known Activations