INDEX

Explanations

references to the concept of "wholeness" or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

…

-0.53

、

-0.51

“

-0.50

ok

-0.50

当

-0.49

врат

-0.44

 live

-0.44

 LIVE

-0.43

「

-0.43

POSITIVE LOGITS

 समीक्षाओं

0.94

RectangleBorder

0.94

WebVitals

0.93

DockStyle

0.90

 unknownFields

0.88

ChildScrollView

0.83

 CreateTagHelper

0.82

RRect

0.82

Datuak

0.82

providedIn

0.80

Activations Density 0.216%

references to the concept of "wholeness" or completeness

No Comments

No Known Activations