INDEX

Explanations

specific tokens related to signaling or markers in a scientific or medical context

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

 دیکھیے

-0.80

 erop

-0.70

 propOrder

-0.66

ंदीखरीदारी

-0.63

 beginnetje

-0.63

ništvo

-0.63

 Statt

-0.62

География

-0.61

❋

-0.61

 mergeFrom

-0.59

POSITIVE LOGITS

hematical

0.87

א

0.81

פ

0.81

अ

0.81

Α

0.80

ब

0.78

ا

0.78

setH

0.78

מ

0.77

ב

0.76

Activations Density 0.076%

specific tokens related to signaling or markers in a scientific or medical context

No Comments

No Known Activations