INDEX

Explanations

words and phrases related to online postings and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

getColumnIndex

-0.79

ArgsConstructor

-0.76

ecore

-0.73

 CoreData

-0.71

__":

-0.69

 Khat

-0.69

 Gaut

-0.66

aleza

-0.63

SPATH

-0.63

 considérons

-0.62

POSITIVE LOGITS

 posted

1.05

 myſelf

1.05

 themſelves

0.99

 Theſe

0.99

Posted

0.92

 posting

0.91

 whoſe

0.90

 ſeveral

0.88

 himſelf

0.87

 Diſ

0.87

Activations Density 0.167%

words and phrases related to online postings and updates

No Comments

No Known Activations