INDEX

Explanations

terms related to medical or clinical studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Lin

-0.64

-0.63

Mo

-0.59

Mar

-0.59

-0.58

Cha

-0.57

il

-0.56

Mat

-0.56

POSITIVE LOGITS

 itſelf

1.33

 myſelf

1.28

 pleaſure

1.25

 purpoſe

1.25

Personensuche

1.23

tagHelperRunner

1.17

 reaſon

1.17

 EconPapers

1.14

 greateſt

1.13

 whoſe

1.12

Activations Density 0.227%

terms related to medical or clinical studies

No Comments

No Known Activations