INDEX

Explanations

mentions of research topics, including medical terms and themes related to cultural perspectives

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

"mention" or similar

np_acts-logits-general · gemini-2.0-flash

mentioning the word

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 noqa

-0.49

marginHorizontal

-0.48

 justified

-0.47

 reasoned

-0.46

<bos>

-0.46

coledì

-0.45

 justification

-0.45

 dramatique

-0.45

 unjustified

-0.43

Justification

-0.43

POSITIVE LOGITS

 mention

1.00

 mentions

0.87

 Mention

0.85

 mencionar

0.80

 BoxDecoration

0.79

 mentioning

0.78

 menciona

0.77

+#+#

0.77

Mention

0.77

 упомина

0.73

Activations Density 0.265%

mentions of research topics, including medical terms and themes related to cultural perspectives

"mention" or similar

mentioning the word

No Comments

No Known Activations