INDEX

Explanations

terms that refer to personal pronouns, particularly 'me' and 'us'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RectangleBorder

-0.63

ssaint

-0.57

rawDesc

-0.56

WriteLiteral

-0.54

tigungs

-0.53

〒

-0.52

mektedir

-0.52

 margen

-0.51

us

-0.50

 ExecuteAsync

-0.50

POSITIVE LOGITS

 SEDS

0.63

basicConfig

0.62

ScopeManager

0.61

 consulté

0.59

ModelAdmin

0.59

RegistryLite

0.58

يكب

0.57

yntaxException

0.57

contentLoaded

0.56

 curative

0.55

Activations Density 0.078%

terms that refer to personal pronouns, particularly 'me' and 'us'

No Comments

No Known Activations