INDEX

Explanations

verbs indicating results or findings from research or experiments

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

IsContent

-0.82

 ſtate

-0.81

 الرياضيه

-0.80

 الحره

-0.80

Geplaatst

-0.79

MigrationBuilder

-0.78

 Majefty

-0.77

IsMutable

-0.76

 houſe

-0.75

 دیکھیے

-0.74

POSITIVE LOGITS

 whereby

0.55

 wherein

0.52

 concernant

0.47

charCodeAt

0.46

 which

0.46

 place

0.45

 therein

0.44

imed

0.44

cuentes

0.41

comparing

0.40

Activations Density 0.788%

verbs indicating results or findings from research or experiments

No Comments

No Known Activations