INDEX

Explanations

proper nouns and key identifiers related to people and organizations

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

!*\

-0.52

↺

-0.48

kün

-0.47

ContentView

-0.46

 Vermögen

-0.46

 losing

-0.45

 further

-0.44

content

-0.44

 novelty

-0.43

 content

-0.43

POSITIVE LOGITS

новниш

0.80

">//

0.76

 EconPapers

0.63

ThroughAttribute

0.63

Бахар

0.61

 متعلقه

0.60

UnusedPrivate

0.58

ValueGenerated

0.57

 CreateTagHelper

0.55

ibouti

0.54

Activations Density 0.265%

proper nouns and key identifiers related to people and organizations

No Comments

No Known Activations