INDEX

Explanations

instances where someone is communicating information or an opinion to someone else using words like "say", "tell", "think", or "said", often focusing on the content being communicated or who is being told what.

oai_token-act-pair · gemini-2.0-flash

telling someone something

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoField

-0.51

ProgressHUD

-0.45

 amé

-0.45

 rythme

-0.44

SharedDtor

-0.44

 خاط

-0.43

ссмо

-0.43

Chham

-0.43

 assumes

-0.43

 Unlimited

-0.42

POSITIVE LOGITS

DeleteBehavior

0.73

 propOrder

0.73

 يتيمه

0.69

 autorytatywna

0.68

 CreateTagHelper

0.63

InjectAttribute

0.59

 Exacts

0.58

 noDo

0.56

 '\\;'

0.55

DockStyle

0.55

Activations Density 2.866%

instances where someone is communicating information or an opinion to someone else using words like "say", "tell", "think", or "said", often focusing on the content being communicated or who is being told what.

telling someone something

No Comments

No Known Activations

instances where someone is communicating information or an opinion to someone else using words like "say", "tell", "think", or "said", often focusing on the content being communicated or who is being told what.

telling someone something

No Comments

No Known Activations