INDEX

Explanations

references to the name "Mo" 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 @ 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

SourceChecksum

-0.74

الحياه

-0.67

extAlignment

-0.63

Personensuche

-0.61

 initComponents

-0.60

مراجع

-0.57

ParallelGroup

-0.57

parsedMessage

-0.56

 Anak

-0.56

BeginInit

-0.55

POSITIVE LOGITS

Mo

3.59

Mo

3.30

mo

3.03

mo

2.54

MO

2.25

MO

1.99

 molybdenum

1.65

 Мо

1.64

Mox

1.55

Moe

1.53

Activations Density 0.050%

references to the name "Mo" and its variations in different contexts

No Comments

No Known Activations