INDEX

Explanations

sentences starting with "I."

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

Sentences starting with "I"

np_acts-logits-general · gemini-2.0-flash

first person subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 hjælp

-0.57

 plads

-0.55

 læng

-0.49

 laikā

-0.49

NoSuchAlgorithm

-0.48

日閲覧

-0.48

 mahdol

-0.48

 gemens

-0.47

 forbin

-0.46

 problemet

-0.45

POSITIVE LOGITS

1.36

1.16

 myself

0.94

myself

0.90

 Myself

0.81

Myself

0.79

my

0.75

0.73

am

0.72

pI

0.71

Activations Density 0.313%

sentences starting with "I."

Sentences starting with "I"

first person subject

No Comments

No Known Activations