INDEX

Explanations

terms related to file processing and state management in programming

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

completed actions or states

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

-0.60

-0.57

<eos>

-0.57

-0.54

-0.53

-0.52

 press

-0.49

“

-0.49

-0.48

POSITIVE LOGITS

 myſelf

1.46

 Jefus

1.26

 itſelf

1.23

 Monfieur

1.19

 Theſe

1.16

ſelf

1.14

 reaſon

1.13

 uſed

1.13

 juſ

1.13

 himſelf

1.13

Activations Density 0.085%

terms related to file processing and state management in programming

completed actions or states

No Comments

No Known Activations