INDEX

Explanations

references to quantities and frequencies in a context

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

quantities

np_acts-logits-general · gemini-2.0-flash

number of times

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

IsContent

-0.47

 pinulongan

-0.45

Sh

-0.42

 element

-0.42

element

-0.42

перед

-0.41

 недель

-0.41

thor

-0.40

HandlerContext

-0.40

ActivityResult

-0.40

POSITIVE LOGITS

 <>",

0.89

 '\\;'

0.78

 betweenstory

0.78

fjspx

0.78

 tartalomajánló

0.77

 kaarangay

0.73

AndEndTag

0.72

 Theſe

0.71

 Waray

0.70

 nonatomic

0.69

Activations Density 0.155%

references to quantities and frequencies in a context

quantities

number of times

No Comments

No Known Activations