INDEX

Explanations

occurrences of the word "as" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-0.72

 Monfieur

-0.72

 myſelf

-0.67

mybatisplus

-0.65

τευ

-0.63

 themſelves

-0.63

ⓧ

-0.61

 whoſe

-0.59

 Anſ

-0.59

 Theſe

-0.59

POSITIVE LOGITS

rungsseite

0.70

extAlignment

0.64

agaimana

0.62

tidaknya

0.61

setupUi

0.59

UpInside

0.58

readAs

0.58

日閲覧

0.56

TabIndex

0.56

 stället

0.56

Activations Density 0.023%

occurrences of the word "as" in various contexts

No Comments

No Known Activations