INDEX

Explanations

references to methods and uses of technology, particularly in relation to healthcare and personal choices

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

"use" or "using."

np_acts-logits-general · gemini-2.0-flash

using methods or technology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.79

 autorytatywna

-0.76

 defaultstate

-0.68

matchCondition

-0.63

malige

-0.61

oneofs

-0.61

참고

-0.59

 gyhoeddwyd

-0.59

WaitGroup

-0.59

 nakalista

-0.58

POSITIVE LOGITS

.*")]

0.58

mybatisplus

0.52

 these

0.52

 ويكيپيديا

0.52

 various

0.48

 ComVisible

0.47

Ārējās

0.46

usercontent

0.45

 Magic

0.45

世上

0.45

Activations Density 0.415%

references to methods and uses of technology, particularly in relation to healthcare and personal choices

"use" or "using."

using methods or technology

No Comments

No Known Activations