INDEX

Explanations

words and phrases that express negative emotions and conflict

oai_token-act-pair · gemini-2.0-flash

commentary

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 charge

-0.59

 challenge

-0.50

 push

-0.50

 project

-0.50

 venture

-0.47

 strain

-0.44

set

-0.43

:],

-0.42

 concern

-0.42

 deal

-0.42

POSITIVE LOGITS

AddTagHelper

0.94

 AssemblyTitle

0.88

OGND

0.81

 للاسماء

0.79

 légiti

0.79

 lenker

0.79

 AssemblyCompany

0.77

 betreft

0.75

Autoritní

0.75

 aveug

0.73

Activations Density 2.451%

words and phrases that express negative emotions and conflict

commentary

No Comments

No Known Activations