INDEX

Explanations

references to programming structures and types

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

code and technical documents

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

TestingModule

-0.59

BufferException

-0.58

CloseOperation

-0.56

featureID

-0.55

 EconPapers

-0.53

protoimpl

-0.52

AddHtmlAttribute

-0.49

UrlResolution

-0.49

dataclass

-0.46

retudo

-0.45

POSITIVE LOGITS

 tartalomajánló

0.49

 препратки

0.41

所在

0.38

DECREF

0.38

esian

0.37

mide

0.37

usc

0.37

mc

0.37

ształ

0.36

 незавершена

0.36

Activations Density 0.051%

references to programming structures and types

code and technical documents

No Comments

No Known Activations