INDEX

Explanations

terms and phrases related to film awards and nominations

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

 auffi

-0.61

 Forumite

-0.60

 Meas

-0.59

tvguidetime

-0.58

 myſelf

-0.58

 HasFactory

-0.56

 iprot

-0.55

 ―――――

-0.55

ließlich

-0.55

 itſelf

-0.54

POSITIVE LOGITS

 Best

0.61

apimachinery

0.59

jsdelivr

0.56

Personendaten

0.50

CreateMap

0.49

antiation

0.49

pyplot

0.49

hyo

0.48

Best

0.47

 best

0.47

Activations Density 0.312%

terms and phrases related to film awards and nominations

No Comments

No Known Activations