INDEX

Explanations

references to "camp" or related activities

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

]='\

-0.92

 виправивши

-0.74

 وتسجيلات

-0.68

 Corbu

-0.64

\}^{

-0.64

]';

-0.64

 Administrativna

-0.63

 reves

-0.61

bootstrapcdn

-0.60

ijas

-0.60

POSITIVE LOGITS

 camp

2.55

 camps

2.47

 CAMP

2.38

Camp

2.32

 Camp

2.28

camp

2.27

 Camps

2.06

CAMP

2.03

camps

1.94

 campers

1.85

Activations Density 0.049%

references to "camp" or related activities

No Comments

No Known Activations