INDEX

Explanations

references to directions and navigation in the text

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

movement or orientation

np_acts-logits-general · gemini-2.0-flash

direction qualifiers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Raised

-0.44

Raised

-0.43

 pozn

-0.43

veen

-0.43

 оригіналу

-0.42

дость

-0.41

cinta

-0.41

stufen

-0.41

 Calvo

-0.41

maine

-0.40

POSITIVE LOGITS

 direction

2.98

 directions

2.67

 Direction

2.54

direction

2.47

 DIRECTION

2.38

Direction

2.27

directions

2.25

 Directions

2.21

DIRECTION

2.00

 direção

1.97

Activations Density 0.262%

references to directions and navigation in the text

movement or orientation

direction qualifiers

No Comments

No Known Activations