INDEX

Explanations

references to external locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 EconPapers

-0.64

gatsby

-0.62

epam

-0.60

eronau

-0.60

raborty

-0.60

formik

-0.59

gorithm

-0.59

 Umsatz

-0.57

borgs

-0.57

er

-0.56

POSITIVE LOGITS

 outside

3.45

 Outside

3.36

Outside

3.33

outside

3.33

 OUTSIDE

3.03

OUTSIDE

2.88

 utanför

2.07

extérieur

2.03

 afuera

1.98

 dehors

1.98

Activations Density 0.073%

references to external locations or entities

No Comments

No Known Activations