INDEX

Explanations

references to horizontal orientation or alignment

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

urgis

-0.72

اً

-0.70

 Jodie

-0.67

 bisogno

-0.66

 McCoy

-0.65

 Riggs

-0.64

initComponents

-0.62

 Nanjing

-0.62

 vilka

-0.62

 Blackman

-0.61

POSITIVE LOGITS

 Horizontal

1.19

 horizontal

1.16

Horizontal

1.14

 horizont

1.13

horizontal

1.10

 breath

1.06

 horizontally

1.05

HORIZONTAL

1.00

breath

0.97

Breath

0.97

Activations Density 0.043%

references to horizontal orientation or alignment

No Comments

No Known Activations