INDEX

Explanations

references to specific years or dates

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

verwijspagina

-0.64

 Kraken

-0.63

搔

-0.62

kaka

-0.57

ddots

-0.57

regional

-0.56

 Myra

-0.56

Skeleton

-0.55

 незавершена

-0.55

 Mare

-0.54

POSITIVE LOGITS

XXI

0.87

xxi

0.80

npos

0.76

 MessageBoxIcon

0.75

 tfsi

0.74

tvguidetime

0.74

ArrowToggle

0.73

VersionUID

0.70

andaag

0.69



0.69

Activations Density 0.103%

references to specific years or dates

No Comments

No Known Activations