INDEX

Explanations

references to household-related topics or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.61

 terce

-0.61

র্ব

-0.60

IsContent

-0.57

 فريبيس

-0.57

 EconPapers

-0.55

romat

-0.55

IntoConstraints

-0.54

 Kemal

-0.54

 Cartes

-0.54

POSITIVE LOGITS

postIndex

0.61

Portail

0.60

closedir

0.58

ographiques

0.54

antMatchers

0.53

StructEnd

0.51

 SqlCommand

0.50

 fondi

0.49

amil

0.47

 ComVisible

0.47

Activations Density 0.132%

references to household-related topics or entities

No Comments

No Known Activations