INDEX

Explanations

phrases that indicate a range of opinions or evaluations about a subject

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

Follows "a," "no," "the," or "your."

np_acts-logits-general · gemini-2.0-flash

identifying qualities or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

TRIBUN

-0.43

 CiNii

-0.38

 Portail

-0.33

Effort

-0.32

else

-0.31

 esfuerzo

-0.30

 soins

-0.29

nologies

-0.29

*/

-0.29

spesies

-0.29

POSITIVE LOGITS

 been

0.88

 tendency

0.81

 difficulty

0.65

 recourse

0.63

 penchant

0.63

 obligation

0.63

sizeCache

0.63

 knack

0.62

 dealings

0.62

 nonUne

0.61

Activations Density 0.279%

phrases that indicate a range of opinions or evaluations about a subject

Follows "a," "no," "the," or "your."

identifying qualities or characteristics

No Comments

No Known Activations