INDEX

Explanations

recurring themes and significant phrases in complex narratives

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

days of the week

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

 refer

-0.25

 formado

-0.22

 formar

-0.21

 prostřed

-0.21

 Praze

-0.20

 București

-0.20

-0.19

 хотели

-0.19

 Praia

-0.18

 form

-0.18

POSITIVE LOGITS

нгред

0.92



0.80

 utafitiHapana

0.80

AISSEE

0.79

 好文分享

0.79

 geweſen

0.77

 deſſen

0.77

 ſuo

0.77

 erſten

0.77

 verſch

0.76

Activations Density 0.012%

recurring themes and significant phrases in complex narratives

days of the week

No Comments

No Known Activations