INDEX

Explanations

questions that seek to understand reasons or motivations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.72

intahan

-0.70

 Cortes

-0.70

")[

-0.67

 Manning

-0.66

 metallo

-0.64

Lass

-0.64

 CGSize

-0.64

DEP

-0.63

ovatel

-0.63

POSITIVE LOGITS

why

1.75

why

1.68

 Whyte

1.61

Why

1.58

Why

1.55

WHY

1.49

WHY

1.48

 Waarom

1.42

 Warum

1.40

 varför

1.34

Activations Density 0.059%

questions that seek to understand reasons or motivations

No Comments

No Known Activations