INDEX

Explanations

the opening of a section or paragraph

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

 للاسماء

-0.74

Autoritní

-0.71

 мәкал

-0.71

 الرياضيه

-0.70

 autorytatywna

-0.69

"+"

-0.60

ientôt

-0.59

!")

-0.59

aarrggbb

-0.58

Jeografia

-0.58

POSITIVE LOGITS

0.72

 Transcript

0.62

 interviewer

0.61

0.60

一同

0.59

 transcript

0.57

Interviewer

0.53

 narrator

0.53

 unison

0.53

:][

0.52

Activations Density 0.254%

the opening of a section or paragraph

No Comments

No Known Activations