INDEX

Explanations

phrases that indicate importance or significance in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 propOrder

-0.89

Rad

-0.60

setVerticalGroup

-0.60

RuleContext

-0.59

 CreateTagHelper

-0.59

 opérateur

-0.59

upsi

-0.58

ModelSerializer

-0.56

 mxArray

-0.56

ويت

-0.55

POSITIVE LOGITS

[]:

0.63

 يتيمه

0.60

 disambiguazione

0.54

ACHUSETTS

0.52

 فريبيس

0.50

\{\\

0.49

sizlik

0.49

 okuyayım

0.48

jspb

0.48

 beban

0.47

Activations Density 0.109%

phrases that indicate importance or significance in a context

No Comments

No Known Activations