INDEX

Explanations

words related to physical actions or processes

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

Grasping, holding, or ergonomic features

np_acts-logits-general · gemini-2.0-flash

grip and handles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 undef

-0.53

 diplomacy

-0.52

Wyn

-0.51

aigu

-0.50

 supersonic

-0.48

 rasc

-0.48

 automata

-0.47

 tabulation

-0.46

 diaphragm

-0.46

 Automata

-0.46

POSITIVE LOGITS

 grip

1.51

 grips

1.33

 Grip

1.25

grip

1.20

 hold

1.15

Grip

1.13

 gripping

1.12

 gripped

1.09

hold

1.07

 handles

1.06

Activations Density 0.259%

words related to physical actions or processes

Grasping, holding, or ergonomic features

grip and handles

No Comments

No Known Activations