INDEX

Explanations

references to historical timelines and dates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

archiviato

-0.60

!\!\

-0.56

iric

-0.56

 createState

-0.55

\}\\

-0.54

"{\

-0.54

chiat

-0.54

 davon

-0.53

 Jaco

-0.53

 Bask

-0.52

POSITIVE LOGITS

TagMode

0.73

 kasarigan

0.68

$_['

0.66

 députés

0.65

Portale

0.62

InjectAttribute

0.56

 déput

0.55

 ekor

0.55

okovic

0.54

 елның

0.53

Activations Density 0.191%

references to historical timelines and dates

No Comments

No Known Activations