INDEX

Explanations

expressions of personal growth and self-acceptance

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

time or frequency

np_acts-logits-general · gemini-2.0-flash

recent time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 yourselves

-0.67

私も

-0.63

僕も

-0.63

ご注意

-0.61

we

-0.59

 silahkan

-0.57

彼らは

-0.54

 themselves

-0.54

themselves

-0.53

herself

-0.53

POSITIVE LOGITS

 Lately

1.23

 lately

1.19

 Recently

0.98

Recently

0.95

 recently

0.93

recently

0.89

 whenever

0.85

 everytime

0.84

 Whenever

0.84

 Occasionally

0.83

Activations Density 0.336%

expressions of personal growth and self-acceptance

time or frequency

recent time periods

No Comments

No Known Activations