INDEX

Explanations

instances of the word "able" indicating capability or potential

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mors

-0.79

YSIS

-0.70

DoubleQuotes

-0.68

upsi

-0.68

indon

-0.67

 dwarfs

-0.66

र्ष

-0.64

רושלים

-0.64

 Rees

-0.63

 seznam

-0.63

POSITIVE LOGITS

 able

1.61

 Able

1.48

Able

1.34

 Ability

1.20

 ability

1.12

Ability

1.10

 abilities

1.03

 Abilities

0.94

Abilities

0.92

 capaces

0.90

Activations Density 0.069%

instances of the word "able" indicating capability or potential

No Comments

No Known Activations