INDEX

Explanations

references to content-related topics or categories

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

"Content" followed by various terms

np_acts-logits-general · gemini-2.0-flash

content analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.57

Havolalar

-0.55

+#+#

-0.55

 AssemblyTitle

-0.52

 MainAxisSize

-0.52

RegressionTest

-0.51

 tartalomajánló

-0.50

ंदीखरीदारी

-0.49

 onPostExecute

-0.49

jsxFileName

-0.49

POSITIVE LOGITS

 Content

0.75

Content

0.66

 content

0.64

 CONTENT

0.63

 getContent

0.61

content

0.60

getContent

0.54

ontent

0.52

CONTENT

0.52

 setContent

0.51

Activations Density 0.088%

references to content-related topics or categories

"Content" followed by various terms

content analysis

No Comments

No Known Activations