INDEX

Explanations

instances of the word "same" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 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

navig

-0.54

popo

-0.53

clin

-0.53

<?

-0.51

khu

-0.51

:\/\/

-0.51

octanol

-0.51

 Deriv

-0.50

AnimationsModule

-0.49

lumin

-0.49

POSITIVE LOGITS

 same

2.36

Same

2.19

same

2.13

 Same

2.03

 SAME

1.76

SAME

1.70

 mesmas

1.55

 dezelfde

1.54

 mêmes

1.52

zelfde

1.52

Activations Density 0.182%

instances of the word "same" in various contexts

No Comments

No Known Activations