INDEX

Explanations

references to help and resources related to engineering assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 '\\;'

-0.72

AutoresizingMask

-0.61

комиться

-0.59

SequentialGroup

-0.58

untura

-0.58

 posthum

-0.57

 insuffisamment

-0.57

DataSetChanged

-0.56

 FetchType

-0.56

 initWithFrame

-0.56

POSITIVE LOGITS

 ModelExpression

0.56

 baratas

0.51

 barata

0.50

 billig

0.50

 Krakowie

0.50

MessageTagHelper

0.48

 murah

0.48

 sogget

0.47

 termurah

0.46

 Alquiler

0.46

Activations Density 0.206%

references to help and resources related to engineering assignments

No Comments

No Known Activations