INDEX

Explanations

evaluations of value or worth

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

 gynhyrchwyd

-0.70

rejo

-0.67

 Fische

-0.63

AGC

-0.61

 pData

-0.61

Bue

-0.60

Displays

-0.60

 Landau

-0.60

 słon

-0.59

 Shaksp

-0.59

POSITIVE LOGITS

 worth

2.67

 Worth

2.39

 WORTH

2.38

Worth

2.24

worth

2.15

WORTH

2.02

 worthwhile

1.47

worths

1.20

 Worthy

1.18

 worthy

1.16

Activations Density 0.038%

evaluations of value or worth

No Comments

No Known Activations