INDEX

Explanations

references to laboratory-related terms or experiments

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

 Lein

-0.70

antMatchers

-0.68

openhauer

-0.65

 nomine

-0.65

 Merr

-0.61

 kaynağından

-0.60

bootstrapcdn

-0.60

<tr>

-0.59

 generalised

-0.58

Kuz

-0.58

POSITIVE LOGITS

lab

2.50

 laboratory

2.39

Lab

2.36

 labs

2.28

 Laboratory

2.23

 laboratories

2.20

Lab

2.17

Laboratory

2.11

lab

2.02

LAB

2.01

Activations Density 0.072%

references to laboratory-related terms or experiments

No Comments

No Known Activations