INDEX

Explanations

repeated usage of the word "it."

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

"it" followed by a preposition

np_acts-logits-general · gemini-2.0-flash

it followed by prepositions

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

 propOrder

-0.59

AxisAlignment

-0.56

ed

-0.55

slash

-0.51

học

-0.49

WithMany

-0.49

Française

-0.48

 perfons

-0.47

able

-0.46

加坡

-0.45

POSITIVE LOGITS

alians

0.82

’

0.74

 happen

0.74

 للمعارف

0.71

 habido

0.71

principalTable

0.70

 happening

0.69

+#+#

0.69

 sendiri

0.68

inerary

0.68

Activations Density 0.122%

repeated usage of the word "it."

"it" followed by a preposition

it followed by prepositions

No Comments

No Known Activations