INDEX

Explanations

descriptive phrases and their evaluations, particularly regarding appearance and quality

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

########.

-0.68

FormTagHelper

-0.66

 يتيمه

-0.65

 obscurity

-0.65

بوابة

-0.63

 interpreters

-0.57

onAttach

-0.57

 equator

-0.56

ürger

-0.55

 CanadaChoose

-0.55

POSITIVE LOGITS

 like

1.26

 Like

0.66

 likes

0.65

 seperti

0.63

 quite

0.62

Like

0.62

like

0.60

 good

0.57

 slike

0.56

像是

0.56

Activations Density 0.097%

descriptive phrases and their evaluations, particularly regarding appearance and quality

No Comments

No Known Activations