INDEX

Explanations

references to political dynamics and conflicts, particularly those involving notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 currently

-0.82

 actuellement

-0.82

currently

-0.75

 attualmente

-0.75

 ieri

-0.69

 yesterday

-0.69

 recent

-0.68

 Currently

-0.68

 actualmente

-0.66

yesterday

-0.66

POSITIVE LOGITS

 later

0.64

Later

0.62

 Later

0.61

later

0.61

 pozdě

0.60

 soon

0.59

 poté

0.57

 später

0.54

此时的

0.54

Eventually

0.53

Activations Density 1.961%

references to political dynamics and conflicts, particularly those involving notable figures

No Comments

No Known Activations