INDEX

Explanations

terms related to research articles and their attributes, specifically focusing on methodologies and data contributions

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

asinya

-0.52

XmlRootElement

-0.48

vio

-0.47

posedge

-0.47

isissez

-0.47

retin

-0.44

rat

-0.43

 cipolla

-0.42

co

-0.42

 Survey

-0.41

POSITIVE LOGITS

 للمعارف

1.09

 EconPapers

1.00

ThroughAttribute

0.93

tanleria

0.91

etc

0.91

 <<<<<<<<<<<<<<

0.90

 فريبيس

0.89

IsContent

0.86

UnusedPrivate

0.85

TextHelper

0.84

Activations Density 1.234%

terms related to research articles and their attributes, specifically focusing on methodologies and data contributions

No Comments

No Known Activations