INDEX

Explanations

the beginning of document sections or headers related to programming or server configurations

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

specific labels

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

 InputDecoration

-0.93

 BoxDecoration

-0.83

تقاوى

-0.82

Datuak

-0.81

AddTagHelper

-0.77

setVerticalGroup

-0.77

 CreateTagHelper

-0.75

ThroughAttribute

-0.75

 الرياضيه

-0.71

 Мексичка

-0.70

POSITIVE LOGITS

0.55

expandindo

0.52

 production

0.48

 disinf

0.48

 Production

0.47

production

0.46

 Data

0.46

Test

0.44

 Técnica

0.44

tech

0.44

Activations Density 0.165%

the beginning of document sections or headers related to programming or server configurations

specific labels

No Comments

No Known Activations