INDEX

Explanations

phrases that indicate a specific identity or role related to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

expandindo

-0.48

exitRule

-0.47

Hentet

-0.45

⁩

-0.45

-0.44

ripe

-0.42

simmon

-0.42

-0.41

contentLoaded

-0.40

POSITIVE LOGITS

 فريبيس

0.50

ngdoc

0.50

 Sebagai

0.46

 Arbeitgeber

0.46

älv

0.45

Sebagai

0.42

 Auß

0.42

TagNumber

0.41

niająca

0.41

 intérêts

0.41

Activations Density 0.191%

phrases that indicate a specific identity or role related to individuals or entities

No Comments

No Known Activations