INDEX

Explanations

words related to medicine, health, and safety

oai_token-act-pair · gemini-2.0-flash

variations of the word "active"

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

active

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

Not in Any Lists

No Comments

Negative Logits

олові

-0.68

 Programs

-0.61

RegressionTest

-0.60

 tiens

-0.55

RegistryLite

-0.55

onden

-0.55

Protocols

-0.54

 PROGRAMS

-0.53

agues

-0.53

anueva

-0.53

POSITIVE LOGITS

 active

1.18

active

1.05

Active

1.00

 Active

0.97

 ACTIVE

0.85

ACTIVE

0.77

 aktiven

0.73

 side

0.69

 актив

0.68

 actif

0.67

Activations Density 3.556%

words related to medicine, health, and safety

variations of the word "active"

active

No Comments

No Known Activations