INDEX

Explanations

phrases related to return statements in code

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

 pstmt

-0.58

 naselje

-0.49

 doPost

-0.46

 متعلقه

-0.46

databind

-0.46

 lịch

-0.45

preventDefault

-0.43

 subjects

-0.42

Արտաքին

-0.42

Wi

-0.41

POSITIVE LOGITS

 Returns

2.36

Returns

2.33

 returns

2.19

returns

2.07

 RETURNS

1.91

RETURNS

1.66

 retorna

1.12

returning

0.98

 Returning

0.95

 gains

0.95

Activations Density 0.176%

phrases related to return statements in code

No Comments

No Known Activations