INDEX

Explanations

words that express inclusivity or generalization

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pingback

-0.56

prepareStatement

-0.50

✫

-0.49

Слайд

-0.49

expandindo

-0.48

KommentareTeilen

-0.47

Jangan

-0.47

LayoutPanel

-0.47

[]:

-0.47

存于互联网档案馆

-0.46

POSITIVE LOGITS

 كومونز

0.81

All

0.81

 مرئيه

0.79

Datuak

0.78

All

0.73

Each

0.71

TextAppearance

0.66

TextColor

0.65

Every

0.64

 Each

0.64

Activations Density 0.156%

words that express inclusivity or generalization

No Comments

No Known Activations