INDEX

Explanations

technical terms and phrases related to materials, layers, and structures in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

enumi

-0.54

Requires

-0.54

,‎

-0.50

 Requires

-0.48

に進

-0.48

σιμο

-0.47

ędzynarod

-0.47

באנגלית

-0.46

 conséquence

-0.46

mogorov

-0.46

POSITIVE LOGITS

 serve

2.25

 serves

2.15

act

1.97

 acts

1.93

serves

1.88

 serving

1.88

 Serve

1.88

serve

1.84

 Serves

1.84

 acted

1.84

Activations Density 0.883%

technical terms and phrases related to materials, layers, and structures in scientific contexts

No Comments

No Known Activations