INDEX

Explanations

references to academic or professional qualifications

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

Rptr

-0.64

acherous

-0.54

zyw

-0.53

ագրություններ

-0.52

 arXiv

-0.49

дне

-0.48

الحياه

-0.47

Whoever

-0.46

 старости

-0.46

AddHtmlAttribute

-0.46

POSITIVE LOGITS

 summa

1.00

 magna

0.94

cum

0.90

 Summa

0.88

Cum

0.82

 Magna

0.81

magna

0.81

 specializing

0.69

cum

0.66

Cum

0.63

Activations Density 0.112%

references to academic or professional qualifications

No Comments

No Known Activations