INDEX

Explanations

expressions of gratitude and requests for help or advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ⓧ

-0.73

DrawerLayout

-0.67

ArgsConstructor

-0.67

gdx

-0.63

 snippetHide

-0.63

 wireType

-0.61

 onOptions

-0.61

ScopeManager

-0.61

SourceChecksum

-0.55

TagMode

-0.55

POSITIVE LOGITS

 advance

2.26

 ahead

2.25

 beforehand

2.07

 AHEAD

1.82

ahead

1.81

 Ahead

1.79

advance

1.79

 Advance

1.77

Ahead

1.69

Advance

1.67

Activations Density 0.285%

expressions of gratitude and requests for help or advice

No Comments

No Known Activations