INDEX

Explanations

phrases that indicate quality or ranking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

loroethene

-0.72

</i>

-0.69

</b>

-0.65

flug

-0.65

 gustó

-0.63

Ẽ

-0.62

iség

-0.62

 AssemblyCompany

-0.61

Renault

-0.59

huawei

-0.59

POSITIVE LOGITS

TOP

1.72

TOP

1.51

 Tops

1.48

 tops

1.45

Top

1.43

Top

1.35

top

1.34

top

1.34

getTop

1.25

tops

1.20

Activations Density 0.100%

phrases that indicate quality or ranking

No Comments

No Known Activations