INDEX

Explanations

references to relationships and interactions between people

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

Follows "to" with "know"

np_acts-logits-general · gemini-2.0-flash

know it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

hithe

-0.60

 nakalista

-0.53

Rüyada

-0.52

AVIS

-0.49

ʖ

-0.49

WebElementEntity

-0.48

illeur

-0.48

']).

-0.47

ЙТЕ

-0.46

Sig

-0.45

POSITIVE LOGITS

 know

1.56

 knew

1.44

 knowing

1.40

 knows

1.39

know

1.39

 known

1.35

 Know

1.34

Know

1.32

 Knowing

1.30

Knowing

1.25

Activations Density 0.138%

references to relationships and interactions between people

Follows "to" with "know"

know it

No Comments

No Known Activations