INDEX

Explanations

words related to population metrics and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ंदीखरीदारी

-0.62

saraba

-0.59

esez

-0.57

 חיצוניים

-0.57

 téc

-0.51

 /\.(

-0.49

ENBERG

-0.49

 courbe

-0.49

 Tomé

-0.48

Fag

-0.48

POSITIVE LOGITS

ulated

0.69

__':

0.69

__':

0.69

 يتيمه

0.67

ulate

0.62

innerHTML

0.61

ules

0.60

ulates

0.60

Ram

0.60

 cues

0.59

Activations Density 2.248%

words related to population metrics and calculations

No Comments

No Known Activations