INDEX

Explanations

values associated with error handling or status codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

出版年

-0.60

veste

-0.51

inderella

-0.50

सन्दर्भ

-0.49

webElementXpaths

-0.49

urah

-0.48

ital

-0.46

Autoritní

-0.46

 utafitiHapana

-0.45

CastException

-0.44

POSITIVE LOGITS

IntoConstraints

0.69

:✨

0.63

0.60

 BrowserModule

0.59

SourceChecksum

0.58

loroethene

0.58

 esternos

0.58

 étoit

0.56

 Barbuda

0.55

Anhalt

0.55

Activations Density 0.035%

values associated with error handling or status codes

No Comments

No Known Activations