INDEX

Explanations

the word "forget," along with words suggesting a mild negation or push-back

oai_token-act-pair · gemini-2.0-flash

forget

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 autorytatywna

-0.79

 صوتيه

-0.78

 تانيه

-0.78

fjspx

-0.71

expandindo

-0.70

 Roskov

-0.69

RefNanny

-0.69

 ddelweddau

-0.68

tvguidetime

-0.66

AddTagHelper

-0.66

POSITIVE LOGITS

 Turning

0.46

 remained

0.46

Turning

0.45

 turning

0.45

<bos>

0.44

enda

0.43

ver

0.42

VersionUID

0.42

體

0.42

Activations Density 0.667%

the word "forget," along with words suggesting a mild negation or push-back

forget

No Comments

No Known Activations