INDEX

Explanations

references to "state" in various contexts within the text

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

"state" followed by specific punctuation or words

np_acts-logits-general · gemini-2.0-flash

state or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 kaarangay

-0.67

uxxxx

-0.60

 noDo

-0.58

 Preferencias

-0.51

 doInBackground

-0.51

doug

-0.50

Hug

-0.49

FunctionFlags

-0.48

ribbon

-0.48

urgery

-0.48

POSITIVE LOGITS

 state

1.25

 State

1.24

State

1.23

 STATE

1.12

state

1.07

STATE

1.04

 ſtate

0.96

 ftate

0.96

getState

0.93

 getState

0.93

Activations Density 0.139%

references to "state" in various contexts within the text

"state" followed by specific punctuation or words

state or states

No Comments

No Known Activations