INDEX

Explanations

formal instructions and procedural language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Geplaatst

-0.80

DockStyle

-0.80

Parcelize

-0.78

 CreateTagHelper

-0.69

PreferredItem

-0.64

webElementXpaths

-0.63

StructEnd

-0.60

ValueStyle

-0.58

AddTagHelper

-0.58

stateMutability

-0.57

POSITIVE LOGITS

saraba

0.54

 insuffisamment

0.50

 hendak

0.48

ewon

0.48

 belangrijk

0.46

 should

0.46

どうしても

0.46

際は

0.46

 externi

0.45

ForKey

0.45

Activations Density 0.440%

formal instructions and procedural language

No Comments

No Known Activations