INDEX

Explanations

instances of personal pronouns and related phrases in a conversational context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"I" followed by a verb

np_acts-logits-general · gemini-2.0-flash

I statements expressing feelings or thoughts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.66

roek

-0.65

createStatement

-0.61

DoubleQuotes

-0.61

kloped

-0.60

Răsp

-0.60

RenderAtEndOf

-0.56

 EXPERI

-0.55

Witam

-0.55

requireNonNull

-0.55

POSITIVE LOGITS

 wonder

0.73

 hope

0.64

 hâte

0.57

 forgot

0.57

wonder

0.54

 think

0.54

bet

0.54

 kind

0.52

 autorytatywna

0.52

 wondering

0.51

Activations Density 0.206%

instances of personal pronouns and related phrases in a conversational context

"I" followed by a verb

I statements expressing feelings or thoughts

No Comments

No Known Activations