INDEX

Explanations

key terms and phrases associated with reports and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ANTAGES

-0.70

Configurer

-0.68

 CGRectMake

-0.66

ServletException

-0.61

MeasureSpec

-0.61

LikeLike

-0.60

CGRectMake

-0.60

endswith

-0.59

XmlAccessType

-0.59

softc

-0.58

POSITIVE LOGITS

 printed

0.59

dsc

0.59

 digest

0.57

 inquirer

0.56

 text

0.55

 decipher

0.54

 linkovi

0.53

 հղումներ

0.52

 comments

0.52

 comment

0.51

Activations Density 1.920%

key terms and phrases associated with reports and documentation

No Comments

No Known Activations