INDEX

Explanations

references to protein-related concepts, including their expression, interactions, synthesis, and various associated processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.92

assertj

-0.83

 Jann

-0.76

 Ciao

-0.76

ChildScrollView

-0.73

 InputDecoration

-0.72

 Vict

-0.72

 tramway

-0.70

 Shakspeare

-0.70

 esquerdo

-0.70

POSITIVE LOGITS

 protein

2.23

protein

2.19

 Protein

2.13

Protein

2.05

 proteins

1.99

 PROTEIN

1.90

 Proteins

1.87

Proteins

1.86

proteins

1.63

蛋白

1.47

Activations Density 0.138%

references to protein-related concepts, including their expression, interactions, synthesis, and various associated processes

No Comments

No Known Activations