INDEX

Explanations

occurrences of function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

PageContext

-0.51

शन

-0.51

 Ulla

-0.50

isand

-0.49

-0.48

bre

-0.48

 system

-0.48

iah

-0.48

 Carver

-0.47

POSITIVE LOGITS

func

3.38

 func

2.60

Func

1.63

 Func

1.52

FUNC

1.30

funcs

1.21

Funcs

1.16

ConstraintMaker

1.06

CppMethod

1.00

 FUNC

0.93

Activations Density 0.085%

occurrences of function definitions

No Comments

No Known Activations