INDEX

Explanations

medical and scientific terms related to health treatments and assessments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$_"

-0.76

RenderAtEndOf

-0.71

 CreateTagHelper

-0.71

 Paglinawan

-0.69

Datuak

-0.66

 userSchema

-0.61

reht

-0.60

 سكانية

-0.60

 <>",

-0.60

*/;

-0.59

POSITIVE LOGITS

®

0.86

®.

0.68

®,

0.67

Viited

0.63

©

0.63

contentLoaded

0.60

Ⓡ

0.58

®

0.57

™

0.56

®-

0.52

Activations Density 0.565%

medical and scientific terms related to health treatments and assessments

No Comments

No Known Activations