INDEX

Explanations

patterns related to code structure and library usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

WriteBarrier

-0.93

 дописавши

-0.92

EDEFAULT

-0.90

uxxxx

-0.87

MethodManager

-0.85

awtextra

-0.84

iNdEx

-0.81

multer

-0.79

IntoConstraints

-0.79

 nakalista

-0.78

POSITIVE LOGITS

 vertik

0.53

Rüyada

0.49

ressing

0.48

实

0.48

sumowanie

0.48

psk

0.47

Dey

0.47

ποι

0.47

 jadx

0.46

зей

0.46

Activations Density 0.078%

patterns related to code structure and library usage

No Comments

No Known Activations