INDEX

Explanations

references to geographic locations and their associations with specific entities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

resp

-0.51

ínsula

-0.47

zał

-0.46

espère

-0.45

亿元

-0.43

 Deans

-0.43

HttpEntity

-0.43

ніципалі

-0.43

ễn

-0.42

 Niedersachsen

-0.42

POSITIVE LOGITS

Personendaten

0.92

 resourceCulture

0.86

 propOrder

0.82

NameInMap

0.82

Hentet

0.75

 AssemblyCulture

0.74

AndEndTag

0.72

Билгалдахарш

0.68

expandindo

0.67

Rohy

0.66

Activations Density 0.269%

references to geographic locations and their associations with specific entities or events

No Comments

No Known Activations