INDEX

Explanations

interactions involving personal identity and self-perception

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

+#+#

-0.90

essoas

-0.73

 متعلقه

-0.73

ValueStyle

-0.69

 Monfieur

-0.66

 themſelves

-0.65

 Jefus

-0.64

WithIOException

-0.63

tagHelperRunner

-0.63

 doubtnut

-0.61

POSITIVE LOGITS

__":

0.54

“

0.52

ライダー

0.52

kloped

0.49

ecore

0.46

__':

0.46

aternion

0.44

car

0.44

 DevExpress

0.43

Activations Density 0.315%

interactions involving personal identity and self-perception

No Comments

No Known Activations