INDEX

Explanations

positive sentiments and recommendations regarding experiences or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AnimationsModule

-0.59

 rospy

-0.58

Ārējās

-0.58

ждый

-0.54

\{\\

-0.54

RenderAtEndOf

-0.52

 تضيفلها

-0.51

findpost

-0.51

llon

-0.50

interno

-0.50

POSITIVE LOGITS

Бахар

0.55

<eos>

0.54

ApiModel

0.52

Abitanti

0.51

цтва

0.50

COLUMNS

0.47

marvin

0.46

Javadoc

0.45

WriteLiteral

0.44

complexType

0.43

Activations Density 0.254%

positive sentiments and recommendations regarding experiences or services

No Comments

No Known Activations