INDEX

Explanations

phrases indicating separation or distinction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

dotenv

-0.82

orges

-0.68

SharedCtor

-0.67

type

-0.65

-0.64

styleType

-0.62

volles

-0.61

 type

-0.61

brahim

-0.59

POSITIVE LOGITS

 apart

2.02

apart

1.86

 Apart

1.67

 APART

1.50

Apart

1.49

 aside

1.43

Aside

1.32

aside

1.31

 Aside

1.31

 appart

1.13

Activations Density 0.077%

phrases indicating separation or distinction

No Comments

No Known Activations

phrases indicating separation or distinction

No Comments

No Known Activations