INDEX

Explanations

contents related to physical rehabilitation and therapy

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

"walk" and "walking"

np_acts-logits-general · gemini-2.0-flash

the act of walking

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

AndEndTag

-0.47

ABE

-0.45

Vega

-0.44

SAE

-0.43

 competir

-0.43

 Slee

-0.43

TargetException

-0.43

дие

-0.43

Slee

-0.43

iorna

-0.42

POSITIVE LOGITS

 walk

3.30

 walking

3.26

walk

3.06

walking

2.97

 walks

2.95

 WALK

2.94

 Walk

2.92

 walked

2.91

Walk

2.90

 Walking

2.89

Activations Density 0.326%

contents related to physical rehabilitation and therapy

"walk" and "walking"

the act of walking

No Comments

No Known Activations