INDEX

Explanations

speech attribution, particularly the word "said", and related words like "added"

oai_token-act-pair · gemini-2.0-flash

saying

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 &___

-0.56

stdafx

-0.54

IndentedString

-0.54

 vendus

-0.51

URLException

-0.50

pnea

-0.49

 EnglishChoose

-0.48

clearance

-0.48

τία

-0.47

amkeit

-0.47

POSITIVE LOGITS

 Monfieur

0.56

<bos>

0.51

 saying

0.51

 myſelf

0.49

Portail

0.48

loy

0.47

 Greeks

0.46

]--;

0.46

vosť

0.45

äf

0.44

Activations Density 0.953%

speech attribution, particularly the word "said", and related words like "added"

saying

No Comments

No Known Activations