INDEX

Explanations

inquiries that start with "what."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Verge

-0.68

在于

-0.68

 Linde

-0.67

OfYear

-0.66

COLS

-0.66

 Brook

-0.65

jména

-0.65

 BROOK

-0.65

 brook

-0.65

LINE

-0.64

POSITIVE LOGITS

 what

2.28

what

2.23

 WHAT

2.12

WHAT

2.10

What

2.04

 What

1.95

whats

1.42

 whats

1.24

Whats

1.22

 quelles

1.13

Activations Density 0.104%

inquiries that start with "what."

No Comments

No Known Activations