INDEX

Explanations

phrases indicating relationships or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

probably

-0.58

 prolly

-0.57

 OFDb

-0.56

 Probably

-0.55

 yüzden

-0.54

 probably

-0.54

terase

-0.53

Probably

-0.53

 BEEN

-0.52

енча

-0.51

POSITIVE LOGITS

 everyone

0.77

'{@

0.70

nappropriate

0.65

 everybody

0.64

 each

0.63

0.62

 whatever

0.62

 AssemblyTitle

0.61

blockList

0.60

everyone

0.60

Activations Density 0.191%

phrases indicating relationships or connections between entities

No Comments

No Known Activations