INDEX

Explanations

references to the name "Jonathan" and variations of "Jon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Salve

-0.52

 BoxDecoration

-0.52

NameInMap

-0.51

DockStyle

-0.51

 useAuth

-0.50

TagHelpers

-0.50

tar

-0.48

 ModelExpression

-0.47

 cré

-0.47

étiques

-0.47

POSITIVE LOGITS

AntiForgeryToken

0.90

athon

0.88

 pleaſure

0.70

ScopeManager

0.68

äuser

0.68

 initComponents

0.67

Général

0.66

MLLoader

0.66

ViewImports

0.66

JON

0.65

Activations Density 0.108%

references to the name "Jonathan" and variations of "Jon."

No Comments

No Known Activations