INDEX

Explanations

scientific terms related to research studies and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CodedInputStream

-0.62

variates

-0.56

 itself

-0.55

 оригіналу

-0.52

eau

-0.51

uspiel

-0.50

issex

-0.50

wikidata

-0.48

onedDateTime

-0.48

 rede

-0.48

POSITIVE LOGITS

+#+#

0.65

 виправивши

0.62

AutoScaleMode

0.62

 fieldNum

0.58

Aholisi

0.57

 recev

0.51

initializeApp

0.51

NgModule

0.51

 daarvoor

0.50

 suivent

0.49

Activations Density 0.759%

scientific terms related to research studies and findings

No Comments

No Known Activations