INDEX

Explanations

dimensions and attributes related to layout in markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

oredCriteria

-0.68

 eventdata

-0.66

SequentialGroup

-0.61

 propOrder

-0.61

Erreferentziak

-0.61

 TestBed

-0.59

FieldBuilder

-0.58

 HttpNotFound

-0.58

Referencie

-0.57

Bromoform

-0.57

POSITIVE LOGITS

AnchorStyles

0.59

 ſmall

0.54

 tää

0.53

 scelta

0.49

lös

0.49

 Grie

0.48

 autón

0.47

 Anyways

0.46

 titolo

0.46

stö

0.46

Activations Density 0.059%

dimensions and attributes related to layout in markup languages

No Comments

No Known Activations