INDEX

Explanations

words related to emotional experiences or cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 snippetHide

-0.70

 autorytatywna

-0.67

 estekak

-0.64

 дописавши

-0.63

 EconPapers

-0.63

 Himo

-0.62

OGND

-0.62

saraba

-0.61

WireFormatLite

-0.60

存于互联网档案馆

-0.60

POSITIVE LOGITS

అ

0.38

த

0.37

இ

0.36

அ

0.36

പ

0.36

მ

0.36

ప

0.35

க

0.35

अ

0.35

Activations Density 0.011%

words related to emotional experiences or cultural references

No Comments

No Known Activations