INDEX

Explanations

questions and inquiries requiring clarification or confirmation

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

ing

-0.63

Composable

-0.59

 Leal

-0.56

 Mellon

-0.56

artement

-0.55

 Jeanette

-0.55

Caw

-0.54

っかり

-0.54

 Leger

-0.54

setMinimumSize

-0.54

POSITIVE LOGITS

 does

2.65

 Does

2.47

does

2.43

Does

2.41

 DOES

2.08

DOES

1.97

did

1.44

do

1.38

DID

1.37

doe

1.33

Activations Density 0.069%

questions and inquiries requiring clarification or confirmation

No Comments

No Known Activations