INDEX

Explanations

technical terms related to medical and scientific measurements

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

DoubleQuotes

-0.58

saraba

-0.55

andum

-0.55

 ***!

-0.51

AxisAlignment

-0.51

ening

-0.48

wa

-0.47

الحياه

-0.47

-0.46

FP

-0.46

POSITIVE LOGITS

 RSSSF

0.87

 cdti

0.78

obbies

0.77

 GoogleFonts

0.76

 bricolaje

0.76

drawiam

0.76

]--;

0.75

uawei

0.74

 feroit

0.74

DIPSETTING

0.73

Activations Density 0.760%

technical terms related to medical and scientific measurements

No Comments

No Known Activations