INDEX

Explanations

instances of the word "in" and its variations or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ביוגרפיה

-0.52

sizeCache

-0.48

Enllaces

-0.47

क्

-0.46

Дей

-0.45

 Exacts

-0.45

 blik

-0.45

ánky

-0.44

 rendez

-0.44

IntoConstraints

-0.43

POSITIVE LOGITS

 ThemeData

0.74

]--;

0.68

tvguidetime

0.67

 Include

0.67

".

0.66

"]);

0.63

 INCLUDE

0.63

++

0.62

थि

0.62

Activations Density 0.220%

instances of the word "in" and its variations or related terms

No Comments

No Known Activations