INDEX

Explanations

variations of the word "Am" in different contexts

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

 Meksiku

-0.64

出版年

-0.60

 hini

-0.58

ExtendWith

-0.56

 oprot

-0.56

entile

-0.53

 للمعارف

-0.52

yeti

-0.52

awtextra

-0.52

PyExc

-0.51

POSITIVE LOGITS

Am

0.77

am

0.67

Am

0.66

Ams

0.62

 acorns

0.56

Amo

0.55

Amu

0.54

 Amon

0.54

 putea

0.53

phous

0.53

Activations Density 0.144%

variations of the word "Am" in different contexts

No Comments

No Known Activations