INDEX

Explanations

instances of notable establishments and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Sob

-0.47

Mo

-0.47

 alene

-0.47

TagMode

-0.47

Pa

-0.47

ISupport

-0.47

 '*')

-0.46

 selber

-0.46

 seba

-0.46

 sozinho

-0.46

POSITIVE LOGITS

 nevertheless

0.82

 nonetheless

0.73

 архивлан

0.64

principalColumn

0.62

μως

0.59

RepeatedField

0.58

Rohy

0.58

ponses

0.56

Lähteet

0.56

onViewCreated

0.56

Activations Density 0.255%

instances of notable establishments and their attributes

No Comments

No Known Activations