INDEX

Explanations

the beginning of the document

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

Code snippets and technical questions

np_acts-logits-general · gemini-2.0-flash

web page loading status

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Portale

-0.84

 سكانية

-0.83

 CreateTagHelper

-0.66

achev

-0.65

 Roskov

-0.64

 Majefty

-0.63

 greateſt

-0.63

 noqa

-0.63

 LoginComponent

-0.62

 doubtnut

-0.61

POSITIVE LOGITS

 whether

0.57

 show

0.53

 Show

0.51

 Whether

0.50

InteropServices

0.49

 status

0.48

 state

0.47

whether

0.47

esModule

0.46

contentLoaded

0.45

Activations Density 0.057%

the beginning of the document

Code snippets and technical questions

web page loading status

No Comments

No Known Activations