INDEX

Explanations

mentions of specific individuals or organizations in a media context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.37

nantes

-0.32

 Gemälde

-0.30

Kjelder

-0.30

 escaleras

-0.29

tikzpicture

-0.29

 periódicos

-0.29

adecimal

-0.28

 Jahrgang

-0.28

 schild

-0.28

POSITIVE LOGITS

 unknownFields

0.68

Jereo

0.65

 Италијани

0.64

脚注の使い方

0.63

 للمعارف

0.61

########.

0.60

 ویکی‌پدی

0.59

findpost

0.58

 nakalista

0.57

цездатний

0.56

Activations Density 0.003%

mentions of specific individuals or organizations in a media context

No Comments

No Known Activations