INDEX

Explanations

the beginning of new sections or topics in 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

 myſelf

-0.88

 auffi

-0.84

ⓧ

-0.84

 Roskov

-0.84

contentLoaded

-0.83

Geplaatst

-0.82

Efq

-0.82

)|^{

-0.82

abestanden

-0.82

 ―――――

-0.81

POSITIVE LOGITS

0.62

0.59

0.55

0.54

’

0.53

0.50

 using

0.49

 steder

0.49

 arşivlendi

0.48

IBAction

0.48

Activations Density 0.153%

the beginning of new sections or topics in a document

No Comments

No Known Activations