INDEX

Explanations

references to everyday objects and experiences

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

<bos>

-0.87

 ModelExpression

-0.62

RegressionTest

-0.57

Referințe

-0.57

 InputDecoration

-0.55

日閲覧

-0.54

 regno

-0.53

Gemeinden

-0.53

 hozz

-0.53

ContentLoaded

-0.52

POSITIVE LOGITS

 BorderSide

0.61

клопе

0.57

StoryboardSegue

0.55

BagConstraints

0.55

 carburetor

0.53

ousand

0.52

 mira

0.52

 Embry

0.51

 onOptions

0.51

ositol

0.51

Activations Density 0.694%

references to everyday objects and experiences

No Comments

No Known Activations