INDEX

Explanations

keywords and function calls related to programming and scripting, especially those involving privacy and security elements

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

 rasg

-0.56

 tinta

-0.55

üyada

-0.54

⟶

-0.51

ategy

-0.51

ρός

-0.51

Scream

-0.50

Poppins

-0.50

HasOne

-0.49

 unknownFields

-0.49

POSITIVE LOGITS

存于互联网档案馆

0.85

 EconPapers

0.74

+#+#

0.73

 kaarangay

0.73

jspx

0.72

CloseOperation

0.72

WarningLevel

0.71

 للاسماء

0.71

enumi

0.70

 متعلقه

0.69

Activations Density 0.002%

keywords and function calls related to programming and scripting, especially those involving privacy and security elements

No Comments

No Known Activations