INDEX

Explanations

phrases indicating repetition or frequency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

findElement

-0.80

Portail

-0.79

djangoproject

-0.77

Wpf

-0.76

annica

-0.72

Fixtures

-0.72

 Diab

-0.70

 useDispatch

-0.69

="{{$

-0.68

énario

-0.68

POSITIVE LOGITS

 OVER

1.47

 Over

1.45

Over

1.39

over

1.39

 over

1.38

 Overs

1.32

OVER

1.30

 Overton

1.15

overs

1.14

Overs

1.13

Activations Density 0.124%

phrases indicating repetition or frequency in various contexts

No Comments

No Known Activations