INDEX

Explanations

terms related to medical and biological applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

inį

-0.56

 çiz

-0.48

 veran

-0.47

vil

-0.47

intellij

-0.47

 stille

-0.46

voit

-0.45

Buf

-0.45

-0.44

 independently

-0.44

POSITIVE LOGITS

 كومونز

0.84

ThemeOverlay

0.82

 дописавши

0.82

RenderAtEndOf

0.78

ंदीखरीदारी

0.72

ReusableCell

0.70

 utafitiHapana

0.65

IVEREF

0.64

aarrggbb

0.61

 kaarangay

0.58

Activations Density 1.505%

terms related to medical and biological applications

No Comments

No Known Activations