INDEX

Explanations

programming syntax and structure indicators, such as punctuation and specific characters used in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 crom

-0.53

}*/

-0.50

Ħ

-0.48

пера

-0.48

ym

-0.47

be

-0.47

 whome

-0.47

ze

-0.44

 phenotypic

-0.43

ü

-0.43

POSITIVE LOGITS

 незавершена

0.84

ніципа

0.67

StoryboardSegue

0.64

tvguidetime

0.63

itects

0.61

ImageContext

0.60

^(@)

0.60

 تضيفلها

0.59

CORBA

0.59

 itſelf

0.59

Activations Density 0.634%

programming syntax and structure indicators, such as punctuation and specific characters used in code

No Comments

No Known Activations