INDEX

Explanations

the term "both" indicating duality or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Chriftian

-0.70

Efq

-0.65

DMS

-0.63

 nucleus

-0.62

 Smoky

-0.59

 Silurian

-0.58

 Miao

-0.58

ITC

-0.58

 Rena

-0.58

Bm

-0.58

POSITIVE LOGITS

 both

3.25

both

2.98

Both

2.75

 Both

2.73

BOTH

2.70

 BOTH

2.56

Ambos

2.26

 beide

2.04

 ambos

2.04

 entrambi

2.01

Activations Density 0.082%

the term "both" indicating duality or comparison

No Comments

No Known Activations