INDEX

Explanations

expressions of internal thoughts and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Autoritní

-0.64

kloped

-0.53

elemField

-0.53

AnchorStyles

-0.50

intios

-0.50

JHEP

-0.49

 endian

-0.48

 Shogun

-0.48

ovem

-0.48

omonas

-0.48

POSITIVE LOGITS

 оригіналу

0.73

 kasarigan

0.65

ManagedBean

0.56

 alquiler

0.55

 JpaRepository

0.54

avaient

0.54

AxisAlignment

0.53

EDEFAULT

0.52

 hoped

0.52

 onCreateView

0.52

Activations Density 0.138%

expressions of internal thoughts and emotions

No Comments

No Known Activations