INDEX

Explanations

elements related to control and anxiety in interpersonal contexts

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

punctuation marks

np_acts-logits-general · gemini-2.0-flash

even more, much less

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 myſelf

-0.95

Efq

-0.86

 Majefty

-0.83

 ſtate

-0.81

 reaſon

-0.80

 beſt

-0.80

 purpoſe

-0.79

 ſte

-0.78

 raiſ

-0.77

 itſelf

-0.77

POSITIVE LOGITS

何况

1.09

更何况

1.04

遑

0.99

 apalagi

0.90

 imagine

0.81

 even

0.78

 bahkan

0.72

更

0.72

 Imagine

0.70

Imagine

0.67

Activations Density 0.135%

elements related to control and anxiety in interpersonal contexts

punctuation marks

even more, much less

No Comments

No Known Activations