INDEX

Explanations

coding constructs related to function definitions and variable handling in programming

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

Mathematical expressions and calculations

np_acts-logits-general · gemini-2.0-flash

mathematical or programming questions

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

CppMethod

-0.65

SerializedSize

-0.57

Наводи

-0.52

yntaxException

-0.52

Попис

-0.50

GraphicsUnit

-0.47

AndEndTag

-0.46

copg

-0.46

jsonwebtoken

-0.46

 utafitiHapana

-0.45

POSITIVE LOGITS

addGap

0.43

RenderAtEndOf

0.38

 advies

0.38

 ausged

0.37

 rallado

0.37

 kunde

0.36

pisah

0.36

 bilde

0.36

 према

0.36

OVERR

0.36

Activations Density 0.461%

coding constructs related to function definitions and variable handling in programming

Mathematical expressions and calculations

mathematical or programming questions

No Comments

No Known Activations