INDEX

Explanations

phrases indicating personal reflections or disclosures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

__(/*!

-0.67

ftagPool

-0.60

 Administrativna

-0.59

ebabkan

-0.56

rouvez

-0.56

]=>

-0.55

$_['

-0.55

 Italijanski

-0.54

 eorum

-0.54

ταν

-0.54

POSITIVE LOGITS

余談

1.07

 quick

1.01

FYI

0.99

 note

0.92

FYI

0.92

quick

0.87

Quick

0.86

 siden

0.85

顺便

0.83

 briefly

0.82

Activations Density 0.341%

phrases indicating personal reflections or disclosures

No Comments

No Known Activations