INDEX

Explanations

words or phrases associated with documentation and organization

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

Passive voice and past participles

np_acts-logits-general · gemini-2.0-flash

action and result

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

 الرخصة

-0.78

IntoConstraints

-0.74

GEBURTS

-0.61

:✨

-0.60

évaluateur

-0.56

 doGet

-0.55

 laget

-0.55

 ujednoznacz

-0.54

Triggered

-0.53

 onCancelled

-0.52

POSITIVE LOGITS

put

0.96

 placed

0.83

put

0.83

 distribute

0.83

 resell

0.80

Put

0.80

 handed

0.79

 send

0.78

Put

0.78

 sent

0.77

Activations Density 0.742%

words or phrases associated with documentation and organization

Passive voice and past participles

action and result

No Comments

No Known Activations