INDEX

Explanations

sections that emphasize significant statements or conclusions

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

Text after em-dash

np_acts-logits-general · gemini-2.0-flash

after pauses or punctuation

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

–

-0.83

AndEndTag

-0.83



-0.79

dür

-0.78

––––

-0.74

 أيضاً

-0.73

ureusement

-0.70

LOGGER

-0.70

Obrázky

-0.69

്‍

-0.69

POSITIVE LOGITS

———

1.02

ly

0.94

————————

0.91

————————————————

0.91

—————

0.88

————

0.84

——

0.79

—

0.73

️

0.71

——————

0.71

Activations Density 0.468%

sections that emphasize significant statements or conclusions

Text after em-dash

after pauses or punctuation

No Comments

No Known Activations