INDEX

Explanations

instances of the word "disk."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 auroit

-0.95

 feroit

-0.94

 ſche

-0.92

 ainfi

-0.91

 Infór

-0.89

 ſever

-0.84

 pouvoit

-0.83

 ſou

-0.81

 plufieurs

-0.81

 ſta

-0.80

POSITIVE LOGITS

0.79

0.68

not

0.66

“

0.64

0.63

Sa

0.63

are

0.62

Activations Density 0.615%

instances of the word "disk."

No Comments

No Known Activations