INDEX

Explanations

instances of commands or directives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 calendriers

-0.83

 EconPapers

-0.68

 OMITTED

-0.67

enumii

-0.66

rungsseite

-0.63

uxxxx

-0.63

WEBPACK

-0.61

UMBIA

-0.60

 itself

-0.59

olu

-0.59

POSITIVE LOGITS

接到

0.57

 recib

0.53

 reçoit

0.51

 diminta

0.48

 judiciaire

0.48

 otrzy

0.48

 recev

0.47

 vektör

0.47

 témoin

0.47

 supermercado

0.47

Activations Density 0.517%

instances of commands or directives

No Comments

No Known Activations