INDEX

Explanations

references to rooms or spaces

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

</tfoot>

-0.73

 Réponses

-0.66

::=

-0.64

]--;

-0.64

startAnimation

-0.63

batik

-0.58

ViewFeatures

-0.57

 relève

-0.57

 espirituales

-0.57

 متعلقه

-0.56

POSITIVE LOGITS

 rooms

1.13

rooms

1.08

 Room

1.07

 Rooms

1.04

 room

1.02

 ROOM

0.97

Room

0.95

Rooms

0.93

room

0.92

ROOM

0.91

Activations Density 0.107%

references to rooms or spaces

No Comments

No Known Activations