INDEX

Explanations

terms related to unresolved issues and potential challenges

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

ंदीखरीदारी

-0.71

XmlType

-0.64

Autoritní

-0.64

 Приступљено

-0.62

BagConstraints

-0.60

 useStyles

-0.60

WebElementEntity

-0.60

keyColumn

-0.59

IndentedString

-0.59

 Wicidata

-0.59

POSITIVE LOGITS

un

1.67

未

1.53

 unre

1.50

 undis

1.42

 untouched

1.42

uns

1.42

 unused

1.42

 unfinished

1.40

 undi

1.40

 unsolved

1.38

Activations Density 0.594%

terms related to unresolved issues and potential challenges

No Comments

No Known Activations