INDEX

Explanations

references to chemical compounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

DrawerToggle

-0.79

astify

-0.78

 wounds

-0.75

 trauma

-0.70

 wound

-0.68

getc

-0.68

wound

-0.68

koala

-0.67

SuppressMessage

-0.66

]")]

-0.65

POSITIVE LOGITS

 compound

2.23

 Compound

2.06

 compounds

1.99

Compound

1.98

compound

1.90

 Compounds

1.86

 COMPOUND

1.78

 COMPOUNDS

1.53

 compounded

1.33

 compounding

1.33

Activations Density 0.079%

references to chemical compounds

No Comments

No Known Activations