INDEX

Explanations

specific details about processes or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

évaluateur

-0.71

yntaxException

-0.66

 EconPapers

-0.64

 ModelExpression

-0.60

+#+#

-0.60

Бахар

-0.60

 Alamy

-0.59

 Empieza

-0.57

IVEREF

-0.57



-0.57

POSITIVE LOGITS

 personally

1.52

 persönlich

1.34

 personalmente

1.32

 presencial

1.23

 live

1.16

 személy

1.16

 pessoal

1.14

 лично

1.14

 person

1.12

 physical

1.12

Activations Density 0.194%

specific details about processes or experiences

No Comments

No Known Activations