INDEX

Explanations

the word "for"

oai_token-act-pair · gemini-2.0-flash

for

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Wikimedijinoj

-0.72

 culturelles

-0.63

 vectorielles

-0.63

Stage

-0.58

 Stage

-0.57

 vectoriales

-0.56

GenerationType

-0.55

enumi

-0.55

reas

-0.54

 réal

-0.53

POSITIVE LOGITS

Pautan

0.72

me

0.54

us

0.54

CloseOperation

0.50

 zewnętrzne

0.49

 FontWeight

0.49

 Autorizaciones

0.49

WebServlet

0.48

LayoutPanel

0.48

blica

0.47

Activations Density 1.994%

the word "for"

for

No Comments

No Known Activations