INDEX

Explanations

phrases indicating division or separation into parts or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Cross

-0.48

 CURIAM

-0.46

prav

-0.45

Cross

-0.45

MethodName

-0.43

 Kreuz

-0.41

glected

-0.41

 Mathematik

-0.41

komend

-0.40

CROSS

-0.40

POSITIVE LOGITS

Personensuche

0.98

+#+#

0.95

tagHelperRunner

0.94

MigrationBuilder

0.89

SequentialGroup

0.88

findpost

0.85

AndEndTag

0.85

Datuak

0.80

انيف

0.80

StoryboardSegue

0.80

Activations Density 0.406%

phrases indicating division or separation into parts or categories

No Comments

No Known Activations