INDEX

Explanations

references to previous research and consistency in study findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 giuri

-0.52

multipart

-0.50

 riguarda

-0.50

 interag

-0.50

olism

-0.49

giau

-0.48

Sidney

-0.48

anair

-0.48

 implies

-0.48

 Neub

-0.48

POSITIVE LOGITS

PerformLayout

0.84

 Paglinawan

0.74

IndentedString

0.71

InjectAttribute

0.67

ScopeManager

0.66

 efforts

0.64

 esternos

0.63

 '\\;'

0.63

AnchorStyles

0.63

webElementGuid

0.63

Activations Density 0.563%

references to previous research and consistency in study findings

No Comments

No Known Activations