INDEX

Explanations

geographical names of places

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

 brains

-0.63

-0.60

 اخت

-0.56

non

-0.53

 honor

-0.52

aktery

-0.52

rég

-0.52

delwed

-0.51

do

-0.51

 brain

-0.51

POSITIVE LOGITS

 تضيفلها

0.80

 Савезне

0.76

 Jefus

0.66

 ExecuteAsync

0.65

 avoient

0.65

 définiti

0.64

InstrumentedTest

0.64

 يتيمه

0.64

 ſtre

0.63

 paziente

0.62

Activations Density 0.115%

geographical names of places

No Comments

No Known Activations