INDEX

Explanations

terms related to numerical values and measurements

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

EnableWeb

-0.71

 fréquence

-0.67

+:+

-0.67

omla

-0.67

}_\

-0.65

 gerichtet

-0.63

 varandra

-0.63

ódromo

-0.62

 türlü

-0.62

 opat

-0.62

POSITIVE LOGITS

abs

2.05

abs

2.01

Abs

1.99

Abs

1.90

ABS

1.88

ABS

1.71

 absolu

1.37

 absol

1.22

 Absolute

1.21

 absentee

1.21

Activations Density 0.074%

terms related to numerical values and measurements

No Comments

No Known Activations