INDEX

Explanations

complex commands and definitions related to data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 WaitForSeconds

-0.47

tahui

-0.41

 Stock

-0.41

매

-0.40

Kal

-0.39

kai

-0.39

 nomme

-0.39

กร

-0.39

ного

-0.39

 Bron

-0.38

POSITIVE LOGITS

bit

1.15

bit

1.07

 bits

1.05

 mask

1.03

bits

1.00

 Bits

1.00

Bit

0.99

mask

0.99

Mask

0.98

 Mask

0.98

Activations Density 0.978%

complex commands and definitions related to data processing

No Comments

No Known Activations