INDEX

Explanations

content related to fuel and energy systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 muon

-0.54

horesis

-0.52

tabilis

-0.51

 trout

-0.50

 forceps

-0.49

 Opium

-0.49

 tweezers

-0.49

ysł

-0.49

Jaco

-0.49

 trow

-0.48

POSITIVE LOGITS

 tank

1.43

 tanks

1.39

 Tank

1.31

 Tanks

1.23

 TANK

1.21

Tank

1.21

tank

1.20

tanks

1.16

Tanks

1.12

 tanker

1.10

Activations Density 0.160%

content related to fuel and energy systems

No Comments

No Known Activations