INDEX

Explanations

commands and functions related to input and output operations in programming

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

writing strings

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

 surla

-0.41

 propOrder

-0.40

 CreateTagHelper

-0.39

ISupport

-0.39

atmosphère

-0.38

 về

-0.38

transQ

-0.38

 iArr

-0.38

TabStop

-0.36

assertAll

-0.36

POSITIVE LOGITS

putchar

0.93

putstr

0.77

 oprot

0.52

 Италијани

0.47

MessageTagHelper

0.47

 Majefty

0.46

 pleaſure

0.45

 Савезне

0.44

mul

0.43

DataContract

0.43

Activations Density 0.021%

commands and functions related to input and output operations in programming

writing strings

No Comments

No Known Activations