INDEX

Explanations

mentions of specific individuals, their actions, or attributes in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intenant

-0.41

LookAnd

-0.34

SourceChecksum

-0.34

 encontraban

-0.33

 Match

-0.32

Match

-0.31

 fieldNum

-0.31

PickerController

-0.30

postIndex

-0.29

 match

-0.28

POSITIVE LOGITS

فایل‌لار

0.51

 OMITBAD

0.49

adult

0.49

adults

0.48

ChildScrollView

0.47

 ویکی‌پدیا

0.47

zzleHttp

0.47

 adulti

0.47

vedev

0.47

 adult

0.46

Activations Density 0.166%

mentions of specific individuals, their actions, or attributes in a narrative context

No Comments

No Known Activations