INDEX

Explanations

terms related to medical or scientific annotations and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tvguidetime

-0.84

AsUp

-0.77

 muualla

-0.76

 utafitiHapana

-0.76

StoryboardSegue

-0.74

Sucesor

-0.71

 magasiner

-0.70

 betweenstory

-0.69

niająca

-0.68

 MenuView

-0.68

POSITIVE LOGITS

Ank

0.68

antd

0.67

鱇

0.59

AN

0.57

Anz

0.57

Ans

0.55

 kanyang

0.53

 pinak

0.53

发表于

0.53

Annette

0.52

Activations Density 0.164%

terms related to medical or scientific annotations and classifications

No Comments

No Known Activations