INDEX

Explanations

positive sentiments and relationships involving characters and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ynb

-0.72

consulté

-0.71

soka

-0.70

 transférez

-0.66

itrile

-0.66

GraphicsUnit

-0.66

出版年

-0.65

featureID

-0.65

verwijspagina

-0.65

rosia

-0.65

POSITIVE LOGITS

 especially

0.54

 especialmente

0.49

 lắm

0.46

 Especially

0.45

Especially

0.45

ticularly

0.45

especially

0.44

 Особенно

0.44

 fact

0.43

 additions

0.43

Activations Density 0.313%

positive sentiments and relationships involving characters and experiences

No Comments

No Known Activations