INDEX

Explanations

a variety of potentially controversial topics or statements.

oai_token-act-pair · gemini-2.0-flash

punctuation marks, specifically periods

np_token-act-pair-logits · gpt-4o-mini

period

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 فريبيس

-0.67

GEBURTS

-0.58

NameInMap

-0.57

 nakalista

-0.56

ırken

-0.55

 المعيارى

-0.54

 IBOutlet

-0.52

nloa

-0.51

czyna

-0.51

WebVitals

-0.50

POSITIVE LOGITS

 period

2.44

 Period

2.33

period

2.14

Period

2.13

 PERIOD

1.99

PERIOD

1.71

 periods

1.70

 plain

1.56

 Periods

1.52

periods

1.51

Activations Density 2.294%

a variety of potentially controversial topics or statements.

punctuation marks, specifically periods

period

No Known Activations