INDEX

Explanations

phrases related to customization and editing capabilities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 yoksa

-0.67

才能

-0.65

才会

-0.61

才行

-0.60

才會

-0.57

necessarily

-0.57

먼

-0.54

pires

-0.54

 necesariamente

-0.51

pierw

-0.51

POSITIVE LOGITS

 anytime

1.80

 anywhere

1.78

any

1.65

 easily

1.55

 dowol

1.53

ANY

1.49

anywhere

1.47

 fácilmente

1.39

any

1.36

 Anywhere

1.33

Activations Density 0.892%

phrases related to customization and editing capabilities in various contexts

No Comments

No Known Activations