INDEX

Explanations

verbs indicating state or existence

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

"is" followed by certain words

np_acts-logits-general · gemini-2.0-flash

is/was/were before state or role

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

di

-0.39

 problem

-0.36

dal

-0.34

 Last

-0.34

tonsoft

-0.34

xf

-0.34

sub

-0.34

π

-0.34

π

-0.34

POSITIVE LOGITS

tagHelperRunner

0.81



0.80

 AssemblyCompany

0.74

fromnode

0.73

 mukana

0.67

 étoient

0.63

 Normdatei

0.63

 Económica

0.61

 Signalez

0.60

 étoit

0.59

Activations Density 0.256%

verbs indicating state or existence

"is" followed by certain words

is/was/were before state or role

No Comments

No Known Activations