INDEX

Explanations

terms and concepts related to biological entities and testing, particularly in legal contexts

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

<thead>

-0.50

 BrowserModule

-0.49

UnusedPrivate

-0.48

AddHtmlAttribute

-0.48

ViewFeatures

-0.43

 Ange

-0.41

onso

-0.41

.$

-0.40

uei

-0.40

TagHelper

-0.40

POSITIVE LOGITS

 instead

1.35

instead

1.32

Instead

1.14

 istället

1.10

rather

1.06

 Instead

1.06

 rather

1.06

 anstatt

1.02

 vielmehr

1.00

 invece

0.97

Activations Density 0.827%

terms and concepts related to biological entities and testing, particularly in legal contexts

No Comments

No Known Activations