INDEX

Explanations

sections of text that contain no relevant information or content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Mar

-0.60

mar

-0.52

aged

-0.52

 pinulongan

-0.52

EObject

-0.49

job

-0.49

 standard

-0.48

 standar

-0.48

તા

-0.48

enna

-0.48

POSITIVE LOGITS

tvguidetime

1.04

ergies

0.80

 umbi

0.79

存于互联网档案馆

0.77

 Euchar

0.75

 дописавши

0.75

 Reverso

0.73

theless

0.72

 chakras

0.69

ГЛА

0.67

Activations Density 0.053%

sections of text that contain no relevant information or content

No Comments

No Known Activations