INDEX

Explanations

rhetorical questions seeking clarification or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

UCC

-0.58

erton

-0.53

SSR

-0.50

²(

-0.50

 setLoading

-0.50

GSC

-0.50

CBM

-0.50

rss

-0.50

 Section

-0.50

 Courant

-0.50

POSITIVE LOGITS

Why

1.02

why

1.01

Why

1.00

why

0.98

 Whyte

0.90

WHY

0.88

WHY

0.87

 Pourquoi

0.87

Pourquoi

0.79

Waarom

0.77

Activations Density 0.057%

rhetorical questions seeking clarification or justification

No Comments

No Known Activations