INDEX

Explanations

phrases that describe interactions and relationships between individuals or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.63

 initComponents

-0.52

AutoScaleMode

-0.52

 насељу

-0.51

 cherchés

-0.47

SenderId

-0.47

ؤلاء

-0.47

StackNavigator

-0.47

stateProvider

-0.47

InputElement

-0.47

POSITIVE LOGITS

 each

2.69

 eachother

2.14

each

2.13

 nhau

2.00

 Each

1.90

Each

1.86

 друг

1.79

 EACH

1.69

 varandra

1.58

EACH

1.58

Activations Density 0.348%

phrases that describe interactions and relationships between individuals or objects

No Comments

No Known Activations