INDEX

Explanations

references to concepts of representation and identity

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

"Represent" and its variations

np_acts-logits-general · gemini-2.0-flash

represent

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

Quick

-0.53

 Duplex

-0.52

 Enough

-0.50

-0.48

Fatigue

-0.47

 Pakai

-0.47

Drugs

-0.47

Faster

-0.46

Gut

-0.45

duplex

-0.45

POSITIVE LOGITS

 representation

1.31

 represent

1.23

 REPRESENT

1.20

 Represent

1.18

represent

1.15

 representing

1.14

 represents

1.13

representation

1.11

Represent

1.09

 Representation

1.09

Activations Density 0.211%

references to concepts of representation and identity

"Represent" and its variations

represent

No Comments

No Known Activations