INDEX

Explanations

expressions of gratitude, particularly regarding help received or anticipated

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

Sod

-0.54

ьер

-0.53

ICTS

-0.53

/**

-0.52

こと

-0.51

jord

-0.49

 setLoading

-0.49

 Logger

-0.48

 الس

-0.48

тет

-0.47

POSITIVE LOGITS

 advance

1.53

advance

1.42

 Advance

1.36

Advance

1.30

 ADVANCE

1.28

StructEnd

0.93

 advances

0.88

 تضيفلها

0.85

ADV

0.83

Хьажоргаш

0.82

Activations Density 0.043%

expressions of gratitude, particularly regarding help received or anticipated

No Comments

No Known Activations