INDEX

Explanations

terms related to health, medical conditions, and their treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

###

-0.50

 semelhantes

-0.49

치

-0.47

it

-0.46

 surely

-0.46

 OTHERWISE

-0.45

alike

-0.44

 indeed

-0.44

Linq

-0.44

-0.43

POSITIVE LOGITS

تقاوى

1.06

AnchorStyles

0.93

AccessorTable

0.89

دانشنامهٔ

0.87

 Normdatei

0.86

PhysRevD

0.84

InputBorder

0.82

Personendaten

0.82

 насељу

0.81

 الرياضيه

0.79

Activations Density 0.780%

terms related to health, medical conditions, and their treatments

No Comments

No Known Activations