INDEX

Explanations

references to specific entities and their relationships within a narrative

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

pronouns and names

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

matchCondition

-0.43

 Middle

-0.42

Middle

-0.41

 MIDDLE

-0.41

 middle

-0.40

Rab

-0.39

RAB

-0.38

worked

-0.37

omla

-0.37

 Middleton

-0.37

POSITIVE LOGITS

ftagPool

0.51

styleType

0.48

Portály

0.48

 ThemeData

0.47

Diweddarwch

0.46

 protoimpl

0.44

///</

0.44

 iNdEx

0.44

FormTagHelper

0.43

 betweenstory

0.43

Activations Density 0.097%

references to specific entities and their relationships within a narrative

pronouns and names

No Comments

No Known Activations

references to specific entities and their relationships within a narrative

pronouns and names

No Comments

No Known Activations