INDEX

Explanations

terms related to data analysis, particularly focusing on occurrence and assimilation rates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Malte

-0.61

PRWEB

-0.57

 Tapatalk

-0.54

NewUrlParser

-0.52

 Enkel

-0.52

findpost

-0.51

Datuak

-0.51

SHARE

-0.50

>>;

-0.50

localctx

-0.50

POSITIVE LOGITS

 Assn

0.60

ovací

0.60

 allAfrica

0.59

uxxxx

0.57

 vostri

0.54

éphane

0.52

 mukana

0.52

Soc

0.49

ésult

0.49

aughey

0.49

Activations Density 0.258%

terms related to data analysis, particularly focusing on occurrence and assimilation rates

No Comments

No Known Activations