INDEX

Explanations

phrases related to approval ratings and public opinion metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 autorytatywna

-0.69

ButterKnife

-0.60

\{\\

-0.58

الحياه

-0.53

 виправивши

-0.52

 Harlequin

-0.51

 Indust

-0.50

 industri

-0.48

 quan

-0.48

พัน

-0.48

POSITIVE LOGITS

 polls

0.40

 poll

0.38

denly

0.35

 polling

0.34

twimg

0.34

 Paglinawan

0.33

 wireType

0.33

 voters

0.32

 برانيه

0.32

$_['

0.31

Activations Density 0.197%

phrases related to approval ratings and public opinion metrics

No Comments

No Known Activations