INDEX

Explanations

names and identifiers related to individuals, places, or organizations

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

po

-0.52

nach

-0.46

hkan

-0.46

-0.45

poon

-0.45

ÉE

-0.45

 nach

-0.44

Nonnull

-0.43

 threw

-0.42

GHIJKLM

-0.42

POSITIVE LOGITS

 الحره

0.72

Viitteet

0.72

ंदीखरीदारी

0.71

yntaxException

0.71

évaluateur

0.69

 AssemblyTitle

0.68

Tembelea

0.67

mybatisplus

0.67

+#+

0.65

 autorytatywna

0.65

Activations Density 0.135%

names and identifiers related to individuals, places, or organizations

No Comments

No Known Activations