INDEX

Explanations

phrases indicating a conclusion or decision-making process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 yonder

-0.75

 Siberian

-0.70

 Ural

-0.68

 Hodgkin

-0.68

 houſe

-0.67

 galore

-0.65

 Houſe

-0.65

 Shetland

-0.63

 mignon

-0.63

 Byzantine

-0.63

POSITIVE LOGITS

Rohy

0.74

 reach

0.66

 kasarigan

0.63

Personensuche

0.61

 estimés

0.60

 désolés

0.59

iecie

0.58

 samlet

0.55

 néglig

0.54

بوابة

0.54

Activations Density 0.153%

phrases indicating a conclusion or decision-making process

No Comments

No Known Activations