INDEX

Explanations

references to legal or governmental contexts involving "state" dynamics

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

"state" followed by another word

np_acts-logits-general · gemini-2.0-flash

state of or state court

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 kaarangay

-0.66

 doInBackground

-0.65

 noDo

-0.63

uncher

-0.60

 Preferencias

-0.59

+#+#

-0.58

bbons

-0.57

doug

-0.57

uxxxx

-0.57

Hug

-0.56

POSITIVE LOGITS

 State

1.27

State

1.26

 state

1.24

 STATE

1.13

state

1.12

STATE

1.08

 ſtate

0.94

 ftate

0.93

getState

0.84

 States

0.84

Activations Density 0.110%

references to legal or governmental contexts involving "state" dynamics

"state" followed by another word

state of or state court

No Comments

No Known Activations