INDEX

Explanations

repetitive uses of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 cerveau

-0.52

cipline

-0.51

LastModified

-0.48

 Ανακτήθηκε

-0.48

 közül

-0.48

kaido

-0.47

Boiling

-0.47

 subscript

-0.46

 آنچه

-0.46

 şun

-0.46

POSITIVE LOGITS

Xna

0.79

webElement

0.78

 aDecoder

0.74

 المعيارى

0.74

/*

0.73

 समीक्षक

0.67

that

0.66

("")){

0.64

__":

0.63

}")

0.63

Activations Density 0.156%

repetitive uses of the word "that."

No Comments

No Known Activations