INDEX

Explanations

occurrences of mathematical symbols and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 itſelf

-0.97

 Normdatei

-0.94

曖昧さ回避

-0.94

kháu

-0.94

 Waray

-0.93

DockStyle

-0.93

styleType

-0.93

 typelib

-0.90

 ویکی‌پدی

-0.89

tonode

-0.89

POSITIVE LOGITS

0.61

0.60

0.56

0.53

0.52

颜

0.52

0.51

0.50

Vs

0.49

Activations Density 0.118%

occurrences of mathematical symbols and expressions

No Comments

No Known Activations