INDEX

Explanations

references to various institutes related to neuroscience and electrical engineering

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

gegeven

-0.53

Dimensi

-0.50

WSER

-0.49

 pinulongan

-0.48

λευτα

-0.48

paque

-0.46

skr

-0.46

 Cluster

-0.46

icana

-0.46

ULATED

-0.46

POSITIVE LOGITS

 EconPapers

0.66

ConstraintMaker

0.64

 linkovi

0.60

 Normdatei

0.59

 Biôgrafia

0.58

IsContent

0.57

saraba

0.56

antMatchers

0.55

Portail

0.54

 ddelweddau

0.53

Activations Density 0.388%

references to various institutes related to neuroscience and electrical engineering

No Comments

No Known Activations