INDEX

Explanations

prepositions and their usage within sentences

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

preposition followed by article

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 nahilalakip

-0.88

 queſta

-0.84

:✨

-0.82

 ſche

-0.81

#+#

-0.77

+#+#

-0.75

 ſtate

-0.74

нгред

-0.73

 المعيارى

-0.73

 myſelf

-0.72

POSITIVE LOGITS

0.30

。

0.29

HT

0.29

ly

0.29

at

0.28

AT

0.28

ib

0.28

ld

0.27

was

0.27

Same

0.27

Activations Density 0.100%

prepositions and their usage within sentences

preposition followed by article

No Comments

No Known Activations