INDEX

Explanations

statements and remarks in discussions or dialogues

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

an observation or statement

np_acts-logits-general · gemini-2.0-flash

making or receiving comments and remarks

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

DockStyle

-0.50

 surla

-0.48

Personendaten

-0.48

 Autorizaciones

-0.46

rrggbb

-0.46

CppMethod

-0.44

帖最后由

-0.44

ंदीखरीदारी

-0.43

 wireType

-0.41

 transférez

-0.41

POSITIVE LOGITS

 comments

2.02

 comment

1.94

 remarks

1.81

 Comments

1.69

comments

1.67

comment

1.59

Comments

1.58

 remark

1.56

 Comment

1.53

 commented

1.45

Activations Density 0.339%

statements and remarks in discussions or dialogues

an observation or statement

making or receiving comments and remarks

No Comments

No Known Activations