INDEX

Explanations

terms related to medical procedures and conditions involving "intra" (within) and related anatomical references

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

"intra" prefix, followed by a body-related word

np_acts-logits-general · gemini-2.0-flash

medical terms starting with intra

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

DoubleQuotes

-0.51

原始内容存档

-0.50

 geology

-0.48

tay

-0.48

pology

-0.47

 social

-0.47

erba

-0.46

rification

-0.45

altor

-0.45

CTYPE

-0.45

POSITIVE LOGITS

 disparu

0.75

 remplacé

0.73

 fallu

0.70

 abandonné

0.66

OGND

0.66

 bénéfices

0.66

 colorés

0.64

 vicenda

0.62

ArgsConstructor

0.61

 الحره

0.61

Activations Density 0.702%

terms related to medical procedures and conditions involving "intra" (within) and related anatomical references

"intra" prefix, followed by a body-related word

medical terms starting with intra

No Comments

No Known Activations