INDEX

Explanations

words about strong opinion, agreement or disagreement, and support

oai_token-act-pair · gemini-2.0-flash

opinions expressed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

WriteAttribute

-0.54

Fla

-0.50

Ber

-0.50

multicolumn

-0.49

<eos>

-0.48

AlterField

-0.47

FormatException

-0.46

DllImport

-0.45

addGap

-0.45

이버

-0.45

POSITIVE LOGITS

ніципа

0.85

 Monfieur

0.78

 myſelf

0.71

 itſelf

0.70

 sonore

0.70

 photolibrary

0.68

Efq

0.67

 leſs

0.67

 Houſe

0.67

 Jefus

0.67

Activations Density 0.574%

words about strong opinion, agreement or disagreement, and support

opinions expressed

No Comments

No Known Activations