INDEX

Explanations

technical and scientific terminology related to assumptions and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

TargetException

-0.55

TagHelper

-0.53

IsContent

-0.51

 onCancelled

-0.47

pDialog

-0.47

 windmill

-0.47

тату

-0.43

FontAwesome

-0.42

 проду

-0.42

 miesią

-0.42

POSITIVE LOGITS

WithIOException

0.72

+#+#

0.69

 Wicidata

0.67

 Infórmanos

0.66

 nahilalakip

0.66

 ***!

0.65

ंदीखरीदारी

0.65

 CreateTagHelper

0.62

 transfieras

0.60

SourceChecksum

0.59

Activations Density 0.790%

technical and scientific terminology related to assumptions and measurements

No Comments

No Known Activations