INDEX

Explanations

words that convey strong positive sentiments or appreciations

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

zzi (Ed.), p

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 nahilalakip

-0.93

StoryboardSegue

-0.92

 IndexPath

-0.73

__*/

-0.73

ContentAsync

-0.72

ngdoc

-0.71

lccn

-0.70

новништво

-0.70

WriteBarrier

-0.70

ьаж

-0.69

POSITIVE LOGITS

:✨

0.57

0.52

 very

0.52

 This

0.50

 Very

0.48

This

0.48

fit

0.48

 product

0.48

Very

0.47

 this

0.47

Activations Density 0.005%

words that convey strong positive sentiments or appreciations

zzi (Ed.), p

No Comments

No Known Activations