INDEX

Explanations

phrases or words indicating uncertainty or ambiguity

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

RegressionTest

-0.69

 HasFactory

-0.69

 Dyck

-0.64

 whoſe

-0.63

UnusedPrivate

-0.63

 Jefus

-0.62

 pleaſure

-0.62

Пото

-0.61

 SIAM

-0.60

 poitrine

-0.60

POSITIVE LOGITS

 thing

1.30

 something

1.30

thing

1.26

something

1.23

 things

1.23

 cosa

1.20

THING

1.17

Something

1.16

 Thing

1.16

Thing

1.15

Activations Density 0.147%

phrases or words indicating uncertainty or ambiguity

No Comments

No Known Activations