INDEX

Explanations

instances of the word "saw."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Wikiseite

-0.56

 youthful

-0.44

AxisSize

-0.44

 missione

-0.43

 فريبيس

-0.43

TagHelper

-0.43

uitable

-0.42

wendige

-0.41

 contagious

-0.41

transQ

-0.41

POSITIVE LOGITS

saw

0.80

Saw

0.78

saw

0.76

Saw

0.68

SAW

0.54

SAW

0.45

Investigations

0.44

__":

0.44

 Investigators

0.43

 saws

0.42

Activations Density 0.181%

instances of the word "saw."

No Comments

No Known Activations