INDEX

Explanations

phrases that include the word "look" and its variations, indicating a focus on observation or examination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

feuer

-0.69

SequentialGroup

-0.66

 hossz

-0.65

 Roderick

-0.64

🔥🔥

-0.62

cedures

-0.61

 tarko

-0.61

cisco

-0.60

 comunicarse

-0.59

 huéspedes

-0.59

POSITIVE LOGITS

 View

0.85

Examine

0.84

 VIEW

0.84

 nhìn

0.83

ссмо

0.80

 Examine

0.79

 view

0.78

Viewing

0.78

LOOKING

0.78

Tazama

0.77

Activations Density 0.138%

phrases that include the word "look" and its variations, indicating a focus on observation or examination

No Comments

No Known Activations