INDEX

Explanations

references to achievements and accolades in professional backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

oarece

-0.63

 GenerationType

-0.62

awtextra

-0.62

addCriterion

-0.62

NUMX

-0.58

Izvori

-0.58

aucune

-0.57

essary

-0.57

bersicht

-0.57

 hindsight

-0.56

POSITIVE LOGITS

 Known

0.52

:+:

0.47

 Recently

0.46

he

0.45

 Также

0.44

 Anschließend

0.44

 También

0.44

DoubleQuotes

0.42

 SUDOC

0.42

Также

0.42

Activations Density 0.180%

references to achievements and accolades in professional backgrounds

No Comments

No Known Activations