INDEX

Explanations

phrases that indicate explanations and justifications for phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

expandindo

-0.68

OGND

-0.62

Hauptartikel

-0.57

 Biôgrafia

-0.55

(!__

-0.54

 kasarigan

-0.53

########.

-0.51

 springfox

-0.50

 Photocase

-0.50

unknownFields

-0.50

POSITIVE LOGITS

why

0.56

why

0.47

 mysterious

0.45

 suspiciously

0.45

 varför

0.44

WHY

0.42

 interpreting

0.41

 purposes

0.41

 unexplained

0.40

 observed

0.40

Activations Density 1.612%

phrases that indicate explanations and justifications for phenomena

No Comments

No Known Activations