INDEX

Explanations

references to the sea or ocean-related terms

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

 myſelf

-0.95

 themſelves

-0.90

 purpoſe

-0.88

 Chwiliwch

-0.87

 himſelf

-0.83

μφωνα

-0.82

ciled

-0.80

 itſelf

-0.80

 Primero

-0.78

 antelope

-0.78

POSITIVE LOGITS

Sea

2.05

sea

2.00

Sea

1.91

SEA

1.79

sea

1.68

SEA

1.49

 Seaman

1.01

海

0.99

海

0.98

seag

0.98

Activations Density 0.028%

references to the sea or ocean-related terms

No Comments

No Known Activations