INDEX

Explanations

terms related to protein

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildScrollView

-0.94

 InputDecoration

-0.88

 تضيفلها

-0.83

assertj

-0.82

 Shakspeare

-0.81

 Jann

-0.80

 purpoſe

-0.79

 myſelf

-0.78

 Ciao

-0.77

 Vict

-0.77

POSITIVE LOGITS

protein

1.65

 protein

1.57

 proteins

1.55

 Protein

1.54

 Proteins

1.48

Proteins

1.47

Protein

1.46

 PROTEIN

1.35

proteins

1.22

蛋白

1.12

Activations Density 0.148%

terms related to protein

No Comments

No Known Activations