INDEX

Explanations

keywords and phrases associated with espionage and undercover operations

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

 تضيفلها

-0.61

AutoresizingMask

-0.56

CodedInputStream

-0.56

gdala

-0.55

 NSCoder

-0.54

PDOException

-0.52

ogaster

-0.51

endphp

-0.50

Observed

-0.50

Equal

-0.50

POSITIVE LOGITS

 betrayed

0.67

 BorderRadius

0.66

 betray

0.66

 betraying

0.63

 Judas

0.60

 betrayal

0.58

 traitor

0.56

叛

0.53

 sendiri

0.53

 betrays

0.53

Activations Density 0.487%

keywords and phrases associated with espionage and undercover operations

No Comments

No Known Activations