INDEX

Explanations

terms and concepts related to 3D imaging and stereoscopic displays

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

stā

-0.51

atase

-0.49

 clavier

-0.48

few

-0.48

 fuhr

-0.48

ůměr

-0.47

 MusicBrainz

-0.47

وصلات

-0.47

 răsp

-0.47

 legte

-0.46

POSITIVE LOGITS

imensional

0.96

立体

0.80

archiviato

0.74

 محفوظة

0.73

 立体

0.72

 modeling

0.70

ModelSerializer

0.69

 modelling

0.67

 stere

0.67

 EconPapers

0.66

Activations Density 0.214%

terms and concepts related to 3D imaging and stereoscopic displays

No Comments

No Known Activations