INDEX

Explanations

references to personal emotions or self-related experiences

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

SpringBootTest

-0.81

CloseOperation

-0.72

出版年

-0.72

 themselves

-0.64

forChild

-0.62

utnik

-0.61

 yourselves

-0.60

 transfieras

-0.60

 μας

-0.60

themselves

-0.60

POSITIVE LOGITS

 personally

1.50

 persönlich

1.01

 pribadi

0.96

 personalmente

0.94

 myself

0.89

 лично

0.81

andering

0.77

 Myself

0.77

myself

0.75

 pessoal

0.74

Activations Density 0.054%

references to personal emotions or self-related experiences

No Comments

No Known Activations