INDEX

Explanations

references to shadows in various contexts

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

 المعيارى

-0.86

 miei

-0.76

 initComponents

-0.70

 vostri

-0.70

RIQUE

-0.69

 zufolge

-0.68

 sujets

-0.67

 propOrder

-0.67

Enrique

-0.65

 genitori

-0.64

POSITIVE LOGITS

 shadow

2.83

 Shadow

2.70

shadow

2.58

Shadow

2.51

 shadows

2.41

 SHADOW

2.32

SHADOW

2.20

hadow

2.10

 Shadows

1.99

shadows

1.93

Activations Density 0.035%

references to shadows in various contexts

No Comments

No Known Activations