INDEX

Explanations

references to individuals and their relationships in narratives

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

action verbs followed by context

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

 AssemblyCulture

-0.76

CloseOperation

-0.56

setVerticalGroup

-0.54

__*/

-0.53

EndProject

-0.52

CreateMap

-0.51



-0.51

Portail

-0.51

 initComponents

-0.48

出版年

-0.48

POSITIVE LOGITS

 took

0.39

KI

0.38

="$(

0.37

 intervened

0.37

 emerged

0.36

Mitchell

0.35

 came

0.35

intervention

0.35

 Mitchell

0.34

 secondly

0.33

Activations Density 0.080%

references to individuals and their relationships in narratives

action verbs followed by context

No Comments

No Known Activations