INDEX

Explanations

scientific terms and references from academic literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 gynhyrchwyd

-0.64

 propOrder

-0.62

 automatico

-0.62

writeFieldEnd

-0.62

 Waray

-0.58

essentiel

-0.58

pania

-0.56

neté

-0.55

 sumpay

-0.55

">{{$

-0.54

POSITIVE LOGITS

addContainerGap

0.58

djangoproject

0.52

SuppressMessage

0.51

 հղումներ

0.49

userdetails

0.49

kenstock

0.48

ArgsConstructor

0.48

 GENERATED

0.47

stdc

0.47

webElementXpaths

0.47

Activations Density 6.198%

scientific terms and references from academic literature

No Comments

No Known Activations