INDEX

Explanations

references to specific divisions or departments

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

lccn

-0.83

ⓘ

-0.75

…”

-0.72

 pédagogique

-0.71

 …”

-0.70

逅

-0.66

ínű

-0.66

...”

-0.64

 Flücht

-0.61

 flèche

-0.60

POSITIVE LOGITS

 division

3.15

 Division

3.02

Division

2.80

 divisions

2.75

 DIVISION

2.72

division

2.63

 Divisions

2.59

DIVISION

2.38

divisions

2.15

 divisional

2.01

Activations Density 0.053%

references to specific divisions or departments

No Comments

No Known Activations