INDEX

Explanations

interactions and connections between characters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.68

arithmic

-0.63

 Banten

-0.61

xnn

-0.60

 Codable

-0.59

anteed

-0.56

benhavn

-0.56

omeness

-0.54

ğraf

-0.53

raging

-0.52

POSITIVE LOGITS

henswürdigkeiten

0.67

StoryboardSegue

0.55

 hither

0.55

 yonder

0.52

 accessions

0.52

 Grab

0.52

 spost

0.52

ScopeManager

0.51

COME

0.51

 SEDS

0.50

Activations Density 0.104%

interactions and connections between characters

No Comments

No Known Activations