INDEX

Explanations

technical terms and code-related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 treo

-0.46

 plus

-0.43

him

-0.41

Pal

-0.40

 gidi

-0.39

Pal

-0.38

 πάνω

-0.38

 compromisos

-0.37

 Plus

-0.37

POSITIVE LOGITS

ArrowToggle

0.95

MemoryWarning

0.89

 ―――――

0.89

StoryboardSegue

0.87

IVEREF

0.76

ynb

0.75

DialogContent

0.75

InsertCommand

0.74

medriver

0.74

 MainAxisSize

0.73

Activations Density 0.339%

technical terms and code-related syntax

No Comments

No Known Activations