INDEX

Explanations

phrases indicating tasks or actions that need to be completed or demonstrated

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

Билгалдахарш

-0.87

AndEndTag

-0.80

ftagPool

-0.73

rrggbb

-0.72

Espèce

-0.72

ConstraintMaker

-0.72

 ModelExpression

-0.70

complexContent

-0.67

таратура

-0.65

 noDo

-0.63

POSITIVE LOGITS

 Remaining

0.54

Remaining

0.52

 remaining

0.51

 pozosta

0.47

今度は

0.46

remaining

0.45

Âu

0.45

yaf

0.45

あとは

0.45

 next

0.44

Activations Density 0.333%

phrases indicating tasks or actions that need to be completed or demonstrated

No Comments

No Known Activations