INDEX

Explanations

occurrences of the word "Se" and its variations 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 @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

multer

-0.59

BeginContext

-0.55

routeProvider

-0.53

 background

-0.52

setVerticalGroup

-0.51

τιά

-0.51

 Background

-0.50

appi

-0.50

 idea

-0.50

 callable

-0.49

POSITIVE LOGITS

SourceChecksum

0.50

 незавершена

0.48

AndEndTag

0.48

يكب

0.47

NSE

0.46

 Puede

0.46

ROE

0.45

Ise

0.44



0.44

NSS

0.43

Activations Density 0.107%

occurrences of the word "Se" and its variations in different contexts

No Comments

No Known Activations