INDEX

Explanations

assignment statements and function definitions in code

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

assignments and variables

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

+#+

-0.57

 Autorizaciones

-0.53

 الحره

-0.52

 ब्रेकडाउन

-0.52

 חיצוניים

-0.51

CppMethod

-0.50

 useAppContext

-0.50

IUrlHelper

-0.48

IVEREF

-0.46

 мәкал

-0.46

POSITIVE LOGITS

niająca

0.40

 boîte

0.39

Eksteraj

0.38

 taget

0.38

ウン

0.38

Pä

0.37

Good

0.35

 AssemblyCulture

0.35

 Egan

0.35

 gobern

0.35

Activations Density 0.013%

assignment statements and function definitions in code

assignments and variables

No Comments

No Known Activations