INDEX

Explanations

references to specific software or package names

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Bi

-0.38

Bi

-0.35

-0.33

 self

-0.32

//

-0.31

Mi

-0.31

jspx

-0.31

To

-0.31

POSITIVE LOGITS

desertcart

1.48

 desertcart

0.93

URLException

0.87

 فريبيس

0.78

 betweenstory

0.72

guiente

0.68

iſen

0.68

clerView

0.67

desert

0.66

ientras

0.65

Activations Density 0.000%

references to specific software or package names

<start_of_turn>user

No Comments

No Known Activations