INDEX

Explanations

scientific and mathematical terms related to electrical circuits and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.51

 purpose

-0.51

-0.50

 nahilalakip

-0.47

-0.46

)]{

-0.46

 purposes

-0.45

Ben

-0.45

POSITIVE LOGITS

 ſtate

1.00

 myſelf

0.98

 pleaſure

0.88

 reaſon

0.88

 ſeveral

0.88

 cauſe

0.87

 laſt

0.85

 perſon

0.84

 Diſ

0.84

 ſmall

0.83

Activations Density 0.637%

scientific and mathematical terms related to electrical circuits and measurements

No Comments

No Known Activations