INDEX

Explanations

specific locations or addresses within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 propOrder

-0.60

 мәкалә

-0.57

könyv

-0.56

〗

-0.55

 stiefel

-0.54

 Hershey

-0.54

TableField

-0.53

ſelves

-0.52

simpleType

-0.52

Становништво

-0.51

POSITIVE LOGITS

Referències

0.65

 situé

0.57

ówczas

0.54

templateUrl

0.52

 rumahnya

0.51

 Near

0.49

 justement

0.48

 near

0.48

 принадлежа

0.48

igner

0.48

Activations Density 0.136%

specific locations or addresses within a document

No Comments

No Known Activations