INDEX

Explanations

terms related to forward-looking or anticipatory concepts

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

"forward" or related terms

np_acts-logits-general · gemini-2.0-flash

forward-looking statements

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

 дописавши

-0.51

 getM

-0.47

 Wikimedijinoj

-0.46

COMPLEX

-0.44

AddHtmlAttribute

-0.43

CastException

-0.42

الدراسه

-0.42

 pObj

-0.41

StructEnd

-0.40

 lezioni

-0.40

POSITIVE LOGITS

 forward

2.67

 Forward

2.50

forward

2.45

Forward

2.41

 FORWARD

2.28

FORWARD

2.08

 forwards

2.02

 forwarding

1.71

fwd

1.52

 forwarded

1.45

Activations Density 0.112%

terms related to forward-looking or anticipatory concepts

"forward" or related terms

forward-looking statements

No Comments

No Known Activations