INDEX

Explanations

references to characters and titles of nobility in a conversational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 purpoſe

-1.16

 Monfieur

-1.15

 themſelves

-1.13

 Jefus

-1.09

 متعلقه

-1.09

 auffi

-1.08

$_"

-1.08

 myſelf

-1.07

 itſelf

-1.07

^(@)

-1.07

POSITIVE LOGITS

1.02

0.67

...

0.63

’

0.60

0.57

–

0.57

0.55

…

0.54

Activations Density 0.018%

references to characters and titles of nobility in a conversational context

No Comments

No Known Activations