INDEX

Explanations

discussion about methods and processes in research or technical contexts

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

voerd

-0.61

 '\\;'

-0.57

OGND

-0.57

Reentrant

-0.55

gerichts

-0.54

 iNdEx

-0.54

resultCode

-0.53

jspx

-0.53

 AttributeSet

-0.51

 FishBase

-0.50

POSITIVE LOGITS

 ujednoznacz

0.57

verwijspagina

0.54

 виправивши

0.54

 AssemblyCulture

0.51

AutoresizingMask

0.51

Symbol

0.49

 allows

0.48

 espac

0.48

 fresher

0.47

躇

0.47

Activations Density 0.478%

discussion about methods and processes in research or technical contexts

No Comments

No Known Activations