INDEX

Explanations

references to ethical review and validation in research

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

Obrázky

-0.50

haften

-0.44

rsquo

-0.40

okka

-0.40

mannian

-0.40

its

-0.40

]];

-0.39

фона

-0.39

getSimpleName

-0.38

万円

-0.38

POSITIVE LOGITS

OGND

0.88

WriteTagHelper

0.73

MigrationBuilder

0.67

الإنجليزية

0.65

BufferException

0.64

webElement

0.64

 quæ

0.63

InjectAttribute

0.63

 Reſ

0.62

setopt

0.62

Activations Density 0.261%

references to ethical review and validation in research

No Comments

No Known Activations