INDEX

Explanations

statements about problem-solving or obstacles in a given context

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

Code-related tokens, like collect, process

np_acts-logits-general · gemini-2.0-flash

process files or collect terms

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ManagedBean

-0.44

LLocation

-0.42

AttributeSet

-0.42

AndEndTag

-0.41

ajur

-0.40

ChromeDriver

-0.40

|()

-0.39

 Receiver

-0.39

MouseListener

-0.37

Hochspringen

-0.37

POSITIVE LOGITS

tonsoft

0.50

TextBoxColumn

0.46

rawDesc

0.45

addCriterion

0.44

ंदीखरीदारी

0.44

 resourceCulture

0.44

verifyException

0.43

 propOrder

0.43

yyj

0.43

parsedMessage

0.40

Activations Density 1.670%

statements about problem-solving or obstacles in a given context

Code-related tokens, like collect, process

process files or collect terms

No Comments

No Known Activations