INDEX

Explanations

phrases indicating novelty or previously unexperienced situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

mybatisplus

-0.69

 Legendre

-0.64

 Jind

-0.64

 doubtnut

-0.64

 löyty

-0.62

 againſt

-0.62

IndentedString

-0.62

 foon

-0.61

 pylint

-0.60

Eſ

-0.59

POSITIVE LOGITS

 Never

0.73

 '\\;'

0.72

 ever

0.68

 never

0.64

Never

0.64

Tru

0.63

never

0.62

 Formal

0.61

formal

0.60

 EVER

0.60

Activations Density 0.104%

phrases indicating novelty or previously unexperienced situations

No Comments

No Known Activations