INDEX

Explanations

sentences where the author solicits feedback on their writing, particularly regarding a story

oai_token-act-pair · gemini-2.0-flash

discussion from forums or blogs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

!$

-0.47

GraphicsUnit

-0.47

"$

-0.47

'$

-0.47

queryParams

-0.47

 Vám

-0.46

>{"

-0.44

 dumne

-0.44

FormState

-0.44

Colorado

-0.42

POSITIVE LOGITS

 propOrder

0.75

帖最后由

0.66

ArgsConstructor

0.61

ISupport

0.57

owulf

0.56

 Akismet

0.55

saraba

0.54

 oprot

0.54

 Quake

0.54

uyasha

0.54

Activations Density 43.037%

sentences where the author solicits feedback on their writing, particularly regarding a story

discussion from forums or blogs

No Comments

No Known Activations