INDEX

Explanations

references to specific areas of focus or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 réfugiés

-0.61

rungsseite

-0.58

 passagers

-0.56

 juges

-0.55

 touristes

-0.55

ள்

-0.55

 fiscales

-0.54

 journalistes

-0.53

twimg

-0.53

 salva

-0.53

POSITIVE LOGITS

 areas

2.06

Areas

1.71

 Areas

1.70

 places

1.66

areas

1.64

 AREAS

1.58

 Places

1.33

places

1.32

 PLACES

1.27

Places

1.25

Activations Density 0.134%

references to specific areas of focus or responsibility

No Comments

No Known Activations