INDEX

Explanations

specific identifiers, possibly related to codes, versions, or database entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 bezeichneter

-0.68

 שוליים

-0.64

Autoritní

-0.59

सन्दर्भ

-0.57

multirow

-0.57

 estekak

-0.57

 fhould

-0.56

oredCriteria

-0.55

 myſelf

-0.54

onomía

-0.54

POSITIVE LOGITS

 لينك

0.55

 سرویس

0.47

 محصولات

0.46

 اپل

0.46

лосипе

0.45

 شارژ

0.45

 برند

0.44

 فروشگاه

0.44

 mẽ

0.44

 باتری

0.43

Activations Density 0.005%

specific identifiers, possibly related to codes, versions, or database entries

No Comments

No Known Activations