INDEX

Explanations

phrases indicating conditions or situations that may have changed due to specific events or actions

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

 esboço

-0.53

copg

-0.52

 hâte

-0.52

 equilateral

-0.50

 мәкалә

-0.50

 buurt

-0.49

dresser

-0.49

şiv

-0.49

 onOptions

-0.49

 piaci

-0.49

POSITIVE LOGITS

MigrationBuilder

0.71

stateProvider

0.64

Hochspringen

0.63

audiovisuel

0.63

 ActivatedRoute

0.62

 propOrder

0.61

ThroughAttribute

0.60

pulumi

0.56

ViewFeatures

0.56

 protoimpl

0.54

Activations Density 0.222%

phrases indicating conditions or situations that may have changed due to specific events or actions

No Comments

No Known Activations