INDEX

Explanations

mentions of the word "root" in medical contexts, and sometimes any mention of "patients"

oai_token-act-pair · gemini-2.0-flash

root

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Majefty

-1.55

 purpoſe

-1.53

 ſtate

-1.46

 myſelf

-1.40

Efq

-1.39

 raiſ

-1.38

ſelf

-1.36

 pleaſure

-1.35

 itſelf

-1.34

 ſtand

-1.34

POSITIVE LOGITS

1.00

↵↵

0.93

0.86

<bos>

0.86

0.80

0.77

The

0.76

Activations Density 1.305%

mentions of the word "root" in medical contexts, and sometimes any mention of "patients"

root

No Comments

No Known Activations