INDEX

Explanations

words related to summaries, reviews, and reflecting on past events, often within the context of blog posts or reports

oai_token-act-pair · 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

CompleteListener

-0.64

 Савезне

-0.62

 initComponents

-0.59

็จ

-0.58

=$?

-0.57

 onCancelled

-0.57

例句

-0.56

Efq

-0.55

̈́

-0.54

 IBOutlet

-0.54

POSITIVE LOGITS

UnknownFieldSet

0.55

ніципа

0.55

 estekak

0.54

Hentet

0.52

posedge

0.50

UVWXYZ

0.46

ougars

0.44

 memu

0.44

ValueStyle

0.43

 Messer

0.43

Activations Density 1.662%

words related to summaries, reviews, and reflecting on past events, often within the context of blog posts or reports

No Comments

No Known Activations