INDEX

Explanations

tokens related to names or entities, possibly in a cultural or mythological context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 itſelf

-1.36

 Cæsar

-1.20

 myſelf

-1.19

 Jefus

-1.17

 iſt

-1.16

 Majefty

-1.14

 faſt

-1.08

GeoNames

-1.07

 Houſe

-1.07

 themſelves

-1.05

POSITIVE LOGITS

0.64

0.63

0.62

…

0.61

...

0.60

0.56

an

0.54

↵↵

0.54

0.53

0.52

Activations Density 0.023%

tokens related to names or entities, possibly in a cultural or mythological context

No Comments

No Known Activations