INDEX

Explanations

names of people and places, as well as specific numerical keywords

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

 sacco

-0.71

an

-0.69

 bead

-0.65

 Pelt

-0.63

vang

-0.63

 Bead

-0.62

Kus

-0.62

 depri

-0.62

Tom

-0.61

</b>

-0.61

POSITIVE LOGITS



1.05

 שוליים

1.00

TCG

1.00

 Oakes

0.99

akterysty

0.98

IDL

0.95

 Claremont

0.94

 Lindley

0.94

ropractic

0.94

 Cortés

0.93

Activations Density 2.348%

names of people and places, as well as specific numerical keywords

No Comments

No Known Activations