INDEX

Explanations

transitions or connectors in the text that relate different ideas 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cæsar

-0.65

">*

-0.65

einem

-0.61

tooth

-0.59

 Viter

-0.59

 المعرف

-0.58

herself

-0.57

 deren

-0.56

Efq

-0.55

 Etrus

-0.54

POSITIVE LOGITS

we

1.09

it

1.04

 there

0.91

 they

0.85

0.75

the

0.73

 оригіналу

0.70

you

0.67

帖最后由

0.62

he

0.61

Activations Density 0.525%

transitions or connectors in the text that relate different ideas or events

No Comments

No Known Activations