INDEX

Explanations

details about discussions, events, or presentations involving specific individuals and topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ToListAsync

-0.52

reus

-0.51

SOUNDBITE

-0.49

anglicky

-0.48

 Sleeps

-0.48

外部連結

-0.48

nyata

-0.48

 مدن

-0.48

ppling

-0.48

isted

-0.47

POSITIVE LOGITS

ambung

0.61

 attendees

0.57

 storyteller

0.57

InputBorder

0.56

 presenters

0.55

GOTREF

0.54

 reaſon

0.54

ModelSerializer

0.53

cookieParser

0.52

oneofs

0.52

Activations Density 0.146%

details about discussions, events, or presentations involving specific individuals and topics

No Comments

No Known Activations