INDEX

Explanations

specific sections and mentions related to procedures or guidelines

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

:✨

-0.55

 Pera

-0.52

ENIA

-0.51

 Gost

-0.50

Mutagenicity

-0.50

ntomas

-0.50

ernalia

-0.49

UrlResolution

-0.49

 Савезне

-0.49

 Batam

-0.48

POSITIVE LOGITS

الحياه

0.65

 attiv

0.65

談社

0.63

DotNetBar

0.62

Captor

0.62

 amoureux

0.61

Bronnen

0.61

SequentialGroup

0.61

!*\

0.60

 ddelweddau

0.60

Activations Density 0.044%

specific sections and mentions related to procedures or guidelines

No Comments

No Known Activations