INDEX

Explanations

specific statistical or mathematical terms and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 kasarigan

-0.81

AddTagHelper

-0.77

 ویکی‌پدیا

-0.73

SBATCH

-0.72

 Administrativna

-0.71

 iconTwitter

-0.67

AutoScale

-0.66

OGND

-0.65

 lenker

-0.64

POSITIVE LOGITS

0.68

DebuggerNonUser

0.61

0.57

esgue

0.48

():

0.47

):

0.46

setVerticalGroup

0.43

featureID

0.42

RetentionPolicy

0.42

：

0.40

Activations Density 0.270%

specific statistical or mathematical terms and expressions

No Comments

No Known Activations