INDEX

Explanations

phrases indicating capability or skill

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Fros

-0.70

 MainAxisSize

-0.70

CloseOperation

-0.69

quar

-0.67

 insuffisamment

-0.67

 parseFrom

-0.66

 оригіналу

-0.66

Quar

-0.65

}</

-0.63

Portail

-0.63

POSITIVE LOGITS

 ability

2.38

 Ability

2.20

Ability

2.04

 abilities

2.03

 Abilities

1.77

 capability

1.59

ability

1.55

Abilities

1.43

 Fähigkeit

1.41

 kemampuan

1.39

Activations Density 0.107%

phrases indicating capability or skill

No Comments

No Known Activations